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

Dataset: Open Web Text

Neuron 21 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: 4.4628. Min Range: -4.4628

Max Act: 4.4628. Min Act: -0.1700

Data Index: 7707761 (Open Web Text)

Max Activating Token Index: 343

Text #1

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.4159. Min Act: -0.1700

Data Index: 1160691 (Open Web Text)

Max Activating Token Index: 787

Text #2

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.3005. Min Act: -0.1700

Data Index: 5975142 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.2752. Min Act: -0.1700

Data Index: 3978679 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.2432. Min Act: -0.1700

Data Index: 6722553 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.2120. Min Act: -0.1700

Data Index: 2773321 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.2638. Min Act: -0.1700

Data Index: 1447034 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1877. Min Act: -0.1700

Data Index: 6560602 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.2127. Min Act: -0.1700

Data Index: 4497650 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1926. Min Act: -0.1700

Data Index: 2663242 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1684. Min Act: -0.1700

Data Index: 8686552 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1460. Min Act: -0.1700

Data Index: 7407036 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1452. Min Act: -0.1700

Data Index: 2995734 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1150. Min Act: -0.1700

Data Index: 730854 (Open Web Text)

Max Activating Token Index: 988

Text #14

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1462. Min Act: -0.1700

Data Index: 2695930 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1701. Min Act: -0.1700

Data Index: 201297 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1368. Min Act: -0.1700

Data Index: 3388835 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1448. Min Act: -0.1700

Data Index: 3689982 (Open Web Text)

Max Activating Token Index: 839

Text #18

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1208. Min Act: -0.1700

Data Index: 1856888 (Open Web Text)

Max Activating Token Index: 551

Text #19

Max Range: 4.4628. Min Range: -4.4628

Max Act: 4.1202. Min Act: -0.1700

Data Index: 6634132 (Open Web Text)

Max Activating Token Index: 871