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

Dataset: Open Web Text

Neuron 403 in Layer 4

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: 4.3469. Min Range: -4.3469

Max Act: 4.3469. Min Act: -0.1700

Data Index: 6945044 (Open Web Text)

Max Activating Token Index: 818

Text #1

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.3468. Min Act: -0.1700

Data Index: 1575506 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.3252. Min Act: -0.1700

Data Index: 6479552 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2869. Min Act: -0.1700

Data Index: 8138352 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.3095. Min Act: -0.1700

Data Index: 3279839 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.3101. Min Act: -0.1700

Data Index: 8766076 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2811. Min Act: -0.1700

Data Index: 1560022 (Open Web Text)

Max Activating Token Index: 901

Text #7

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2523. Min Act: -0.1700

Data Index: 2607312 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2541. Min Act: -0.1700

Data Index: 357265 (Open Web Text)

Max Activating Token Index: 557

Text #9

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2644. Min Act: -0.1700

Data Index: 2265403 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2686. Min Act: -0.1700

Data Index: 3985341 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2877. Min Act: -0.1700

Data Index: 1829643 (Open Web Text)

Max Activating Token Index: 352

Text #12

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2545. Min Act: -0.1700

Data Index: 1133762 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2315. Min Act: -0.1700

Data Index: 6073213 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2442. Min Act: -0.1700

Data Index: 3988446 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2453. Min Act: -0.1700

Data Index: 3158718 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2371. Min Act: -0.1700

Data Index: 5885548 (Open Web Text)

Max Activating Token Index: 405

Text #17

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2469. Min Act: -0.1700

Data Index: 5583060 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2156. Min Act: -0.1700

Data Index: 2307573 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 4.3469. Min Range: -4.3469

Max Act: 4.2220. Min Act: -0.1700

Data Index: 3014646 (Open Web Text)

Max Activating Token Index: 942