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

Dataset: Open Web Text

Neuron 53 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: 3.1246. Min Range: -3.1246

Max Act: 3.1246. Min Act: -0.1700

Data Index: 7572374 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 3.1246. Min Range: -3.1246

Max Act: 3.0309. Min Act: -0.1700

Data Index: 886331 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 3.1246. Min Range: -3.1246

Max Act: 3.0118. Min Act: -0.1700

Data Index: 2356724 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9607. Min Act: -0.1700

Data Index: 4422096 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9240. Min Act: -0.1700

Data Index: 2885810 (Open Web Text)

Max Activating Token Index: 749

Text #5

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9517. Min Act: -0.1700

Data Index: 6988842 (Open Web Text)

Max Activating Token Index: 877

Text #6

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9585. Min Act: -0.1700

Data Index: 1377793 (Open Web Text)

Max Activating Token Index: 495

Text #7

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9483. Min Act: -0.1700

Data Index: 7298987 (Open Web Text)

Max Activating Token Index: 122

Text #8

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9618. Min Act: -0.1700

Data Index: 4401931 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9513. Min Act: -0.1700

Data Index: 1397223 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9478. Min Act: -0.1700

Data Index: 6163994 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9153. Min Act: -0.1700

Data Index: 5696628 (Open Web Text)

Max Activating Token Index: 50

Text #12

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9357. Min Act: -0.1700

Data Index: 4922162 (Open Web Text)

Max Activating Token Index: 250

Text #13

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9521. Min Act: -0.1700

Data Index: 1228990 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9055. Min Act: -0.1700

Data Index: 128465 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9044. Min Act: -0.1700

Data Index: 1252219 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9332. Min Act: -0.1700

Data Index: 5269638 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9379. Min Act: -0.1700

Data Index: 627861 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.8924. Min Act: -0.1700

Data Index: 5535635 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 3.1246. Min Range: -3.1246

Max Act: 2.9017. Min Act: -0.1700

Data Index: 1756519 (Open Web Text)

Max Activating Token Index: 885