quantity words like 'some' and 'of'

What this neuron does

This neuron fires on small words that introduce an amount, such as 'some', 'of', 'than' or 'and' right before a number or a count. Turning it up made the model start writing about numbers and counting problems.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   Gertrude has some knowledge of what happened, whether she is mentally unbalanced and is in denial,

2. #2 peak

   missing reliefs and inscriptions.⏎Of the original length of some 158 meters only about 47 meters of the temple remain,

3. #3 peak

   are building. There are some major components up there already, according to Collins. The shuttle has made two trips

4. #4 peak

   a boy). There are some intriguing regional nuances.<|endoftext|>Preparing children for back to school⏎As summer draws to

5. #5 peak

   one of the classes to appear at a PTA meeting. How many ways can the selection be made?⏎College Math 45 -⏎A speaker has a collection of 62 jokes. He uses 3 jokes in each speech.⏎How many

6. #6 peak

   . Every year, more than four hundred million cases of dengue are registered worldwide. It is one of

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   practical challenges are all about making a 'tray' and covering it with paper.⏎My cousin was 24 years old on Friday April 5th in 1974. On what day⏎of the week was she born?⏎

2. #2 peak

   the moon's orbit protected by Earth's magnetosphere (Geophysical Research Letters, DOI: 10.1029/2007GL030507). "

3. #3 peak

   moving along the parabola 4y = (x + 2)^2 in such a way that its x-coordinate is increasing at a constant rate of 2 units per second. How fast is the particle's distance to the point (-

4. #4 peak

   ripetal force acting on a car of mass 2000 Kg turning around a circular bend of radius 50 meters at the constant speed of 36 km/hr?⏎A) 4,000 N⏎B)

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.