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

Dataset: Open Web Text

Neuron 1531 in Layer 5

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: 4.3757. Min Range: -4.3757

Max Act: 4.3757. Min Act: -0.1700

Data Index: 4949774 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.3018. Min Act: -0.1700

Data Index: 8796188 (Open Web Text)

Max Activating Token Index: 940

Text #2

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.2276. Min Act: -0.1700

Data Index: 7977344 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1793. Min Act: -0.1700

Data Index: 6679774 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1688. Min Act: -0.1700

Data Index: 2905518 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1187. Min Act: -0.1700

Data Index: 6318267 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1552. Min Act: -0.1700

Data Index: 1486994 (Open Web Text)

Max Activating Token Index: 863

Text #7

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1336. Min Act: -0.1700

Data Index: 113799 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.1171. Min Act: -0.1700

Data Index: 7219310 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0647. Min Act: -0.1700

Data Index: 1646615 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0789. Min Act: -0.1700

Data Index: 466287 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0702. Min Act: -0.1700

Data Index: 3305159 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0465. Min Act: -0.1700

Data Index: 4146233 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 4.3757. Min Range: -4.3757

Max Act: 3.9869. Min Act: -0.1700

Data Index: 5875408 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0324. Min Act: -0.1700

Data Index: 6463210 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0165. Min Act: -0.1700

Data Index: 5329496 (Open Web Text)

Max Activating Token Index: 939

Text #16

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0159. Min Act: -0.1700

Data Index: 4849552 (Open Web Text)

Max Activating Token Index: 302

Text #17

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0276. Min Act: -0.1700

Data Index: 7885464 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0285. Min Act: -0.1700

Data Index: 4738091 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 4.3757. Min Range: -4.3757

Max Act: 4.0017. Min Act: -0.1700

Data Index: 3585750 (Open Web Text)

Max Activating Token Index: 330