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

Dataset: Open Web Text

Neuron 1425 in Layer 1

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: 1.7494. Min Range: -1.7494

Max Act: 1.7494. Min Act: -0.1700

Data Index: 7797736 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7344. Min Act: -0.1700

Data Index: 2555246 (Open Web Text)

Max Activating Token Index: 899

Text #2

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7228. Min Act: -0.1700

Data Index: 2606072 (Open Web Text)

Max Activating Token Index: 258

Text #3

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7203. Min Act: -0.1700

Data Index: 2300667 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7143. Min Act: -0.1700

Data Index: 694068 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7086. Min Act: -0.1700

Data Index: 230675 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7126. Min Act: -0.1700

Data Index: 8817720 (Open Web Text)

Max Activating Token Index: 199

Text #7

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6969. Min Act: -0.1700

Data Index: 2191037 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.7047. Min Act: -0.1700

Data Index: 104494 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6949. Min Act: -0.1700

Data Index: 2745989 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6780. Min Act: -0.1700

Data Index: 4839471 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6789. Min Act: -0.1700

Data Index: 5810153 (Open Web Text)

Max Activating Token Index: 177

Text #12

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6666. Min Act: -0.1700

Data Index: 4654379 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6627. Min Act: -0.1700

Data Index: 4690656 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6589. Min Act: -0.1700

Data Index: 4452923 (Open Web Text)

Max Activating Token Index: 461

Text #15

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6563. Min Act: -0.1700

Data Index: 7034610 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6552. Min Act: -0.1700

Data Index: 4441102 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6580. Min Act: -0.1700

Data Index: 2211377 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6504. Min Act: -0.1700

Data Index: 8619397 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 1.7494. Min Range: -1.7494

Max Act: 1.6469. Min Act: -0.1700

Data Index: 39638 (Open Web Text)

Max Activating Token Index: 85