Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 466 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9709. Min Act: -0.1700

Data Index: 303989 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9889. Min Act: -0.1700

Data Index: 7690816 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9642. Min Act: -0.1700

Data Index: 704794 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9589. Min Act: -0.1700

Data Index: 6560027 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9440. Min Act: -0.1700

Data Index: 17841 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9330. Min Act: -0.1700

Data Index: 6926197 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9531. Min Act: -0.1700

Data Index: 4144246 (Open Web Text)

Max Activating Token Index: 1012

Text #7

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9188. Min Act: -0.1700

Data Index: 4066370 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8976. Min Act: -0.1700

Data Index: 4394163 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9211. Min Act: -0.1700

Data Index: 2885826 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9240. Min Act: -0.1700

Data Index: 2827560 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8990. Min Act: -0.1700

Data Index: 7557024 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9047. Min Act: -0.1700

Data Index: 3553760 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9007. Min Act: -0.1700

Data Index: 599164 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8978. Min Act: -0.1700

Data Index: 84202 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9134. Min Act: -0.1700

Data Index: 3963633 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9176. Min Act: -0.1700

Data Index: 7340262 (Open Web Text)

Max Activating Token Index: 666

Text #17

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9031. Min Act: -0.1700

Data Index: 3916371 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.9232. Min Act: -0.1700

Data Index: 6108010 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 3.9889. Min Range: -3.9889

Max Act: 3.8674. Min Act: -0.1700

Data Index: 4914442 (Open Web Text)

Max Activating Token Index: 9