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

Dataset: Open Web Text

Neuron 1665 in Layer 2

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: 3.8905. Min Range: -3.8905

Max Act: 3.8905. Min Act: -0.1700

Data Index: 8000013 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8521. Min Act: -0.1700

Data Index: 8000012 (Open Web Text)

Max Activating Token Index: 256

Text #2

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8440. Min Act: -0.1700

Data Index: 2178859 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.8148. Min Act: -0.1700

Data Index: 7324799 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7692. Min Act: -0.1700

Data Index: 8318304 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7576. Min Act: -0.1700

Data Index: 3943380 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.7209. Min Act: -0.1700

Data Index: 6463835 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6757. Min Act: -0.1700

Data Index: 1218724 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6866. Min Act: -0.1700

Data Index: 8289025 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6908. Min Act: -0.1700

Data Index: 7526038 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6499. Min Act: -0.1700

Data Index: 854355 (Open Web Text)

Max Activating Token Index: 480

Text #11

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6418. Min Act: -0.1700

Data Index: 5388543 (Open Web Text)

Max Activating Token Index: 89

Text #12

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6264. Min Act: -0.1700

Data Index: 1474469 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6106. Min Act: -0.1700

Data Index: 8350564 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.5957. Min Act: -0.1700

Data Index: 6413395 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6370. Min Act: -0.1700

Data Index: 3247588 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6177. Min Act: -0.1700

Data Index: 3578831 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6122. Min Act: -0.1700

Data Index: 6966814 (Open Web Text)

Max Activating Token Index: 669

Text #18

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6432. Min Act: -0.1700

Data Index: 8350572 (Open Web Text)

Max Activating Token Index: 847

Text #19

Max Range: 3.8905. Min Range: -3.8905

Max Act: 3.6121. Min Act: -0.1700

Data Index: 5853779 (Open Web Text)

Max Activating Token Index: 462