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

Dataset: Open Web Text

Neuron 1260 in Layer 3

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: 3.2727. Min Range: -3.2727

Max Act: 3.2727. Min Act: -0.1700

Data Index: 7862042 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2551. Min Act: -0.1700

Data Index: 6125417 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1973. Min Act: -0.1700

Data Index: 3133361 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1194. Min Act: -0.1700

Data Index: 5158583 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1338. Min Act: -0.1700

Data Index: 4916460 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1382. Min Act: -0.1700

Data Index: 2897709 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1394. Min Act: -0.1700

Data Index: 399728 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1372. Min Act: -0.1700

Data Index: 3151902 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1153. Min Act: -0.1700

Data Index: 350399 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1357. Min Act: -0.1700

Data Index: 6376461 (Open Web Text)

Max Activating Token Index: 881

Text #10

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1138. Min Act: -0.1700

Data Index: 4574921 (Open Web Text)

Max Activating Token Index: 273

Text #11

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1156. Min Act: -0.1700

Data Index: 7916179 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1243. Min Act: -0.1700

Data Index: 2080337 (Open Web Text)

Max Activating Token Index: 198

Text #13

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1222. Min Act: -0.1700

Data Index: 4949097 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1091. Min Act: -0.1700

Data Index: 880329 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.0968. Min Act: -0.1700

Data Index: 6115004 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1237520 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1010. Min Act: -0.1700

Data Index: 8603107 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1114. Min Act: -0.1700

Data Index: 3861367 (Open Web Text)

Max Activating Token Index: 219

Text #19

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.0655. Min Act: -0.1700

Data Index: 2608 (Open Web Text)

Max Activating Token Index: 99