start-of-document end token

What this neuron does

This neuron lights up on the hidden marker that separates one web page or document from the next. It stays quiet on ordinary words. Turning it up made the model's text wander without a clear theme, so its job seems to be about where a new document begins rather than about any topic.

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

   <|endoftext|>House in Space, from a NASA Remix Challenge. Credit: Cookieater20

2. #2 peak

   <|endoftext|>10 Tips for Parents of Prospective College Students⏎1. Choosing a Career

3. #3 peak

   <|endoftext|>Active transportation refers to non-motorized transportation modes, such as bicycling and

4. #4 peak

   <|endoftext|>Public holidays in Pakistan are different than bank holidays in the country. While all of

5. #5 peak

   <|endoftext|>Philosophy East and West 46 (2):143-

6. #6 peak

   <|endoftext|>Cancer & Tumorigenesis⏎Cancer describes the disease with un

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

   AB 100 AND ARAB 210⏎|SPRING

2. #2 peak

   … Also, poultry must not be left outside the refrigerator for more than two hours.⏎

3. #3 peak

   … Read more<|endoftext|>problem 1: Define the term IT. describe different IT trends

4. #4 peak

   al factors: unbalanced nutrition, excessive exercise and/or trauma⏎Most foals will

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.