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

Dataset: Open Web Text

Neuron 834 in Layer 6

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: 3.1977. Min Range: -3.1977

Max Act: 3.1977. Min Act: -0.1697

Data Index: 5797866 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1977. Min Act: -0.0979

Data Index: 572790 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1808. Min Act: -0.1700

Data Index: 8300096 (Open Web Text)

Max Activating Token Index: 498

Text #3

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1784. Min Act: -0.1620

Data Index: 6494272 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1759. Min Act: -0.1390

Data Index: 6565188 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1544. Min Act: -0.0000

Data Index: 3552460 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1499. Min Act: -0.1565

Data Index: 6035996 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1570. Min Act: -0.1545

Data Index: 4119266 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1510. Min Act: -0.1210

Data Index: 1731456 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1476. Min Act: -0.1700

Data Index: 7930679 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1499. Min Act: -0.1699

Data Index: 3123376 (Open Web Text)

Max Activating Token Index: 518

Text #11

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1371. Min Act: -0.0886

Data Index: 3599106 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1429. Min Act: -0.1679

Data Index: 8727708 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1162. Min Act: -0.1530

Data Index: 7625 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1731455 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1120. Min Act: -0.1691

Data Index: 1053440 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1124. Min Act: -0.1693

Data Index: 3724287 (Open Web Text)

Max Activating Token Index: 176

Text #17

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1151. Min Act: -0.0502

Data Index: 7881850 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1132. Min Act: -0.1654

Data Index: 2737369 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 3.1977. Min Range: -3.1977

Max Act: 3.1243. Min Act: -0.1684

Data Index: 4330526 (Open Web Text)

Max Activating Token Index: 760