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

Dataset: Open Web Text

Neuron 660 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: 3.0397. Min Range: -3.0397

Max Act: 3.0397. Min Act: -0.1700

Data Index: 2678781 (Open Web Text)

Max Activating Token Index: 663

Text #1

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.9202. Min Act: -0.1700

Data Index: 387355 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.8827. Min Act: -0.1700

Data Index: 8273900 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.9099. Min Act: -0.1700

Data Index: 8317810 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.8397. Min Act: -0.1700

Data Index: 5542894 (Open Web Text)

Max Activating Token Index: 985

Text #5

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7883. Min Act: -0.1700

Data Index: 4626296 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.8352. Min Act: -0.1700

Data Index: 4978472 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7859. Min Act: -0.1700

Data Index: 1572347 (Open Web Text)

Max Activating Token Index: 924

Text #8

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7812. Min Act: -0.1700

Data Index: 1993436 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.8263. Min Act: -0.1700

Data Index: 7115164 (Open Web Text)

Max Activating Token Index: 350

Text #10

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7322. Min Act: -0.1700

Data Index: 2676364 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7375. Min Act: -0.1700

Data Index: 8157925 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7097. Min Act: -0.1700

Data Index: 1117196 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7436. Min Act: -0.1700

Data Index: 3081639 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7440. Min Act: -0.1700

Data Index: 6379207 (Open Web Text)

Max Activating Token Index: 531

Text #15

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7065. Min Act: -0.1700

Data Index: 5439055 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7166. Min Act: -0.1700

Data Index: 2034797 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7190. Min Act: -0.1700

Data Index: 7869893 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7073. Min Act: -0.1700

Data Index: 8407190 (Open Web Text)

Max Activating Token Index: 782

Text #19

Max Range: 3.0397. Min Range: -3.0397

Max Act: 2.7097. Min Act: -0.1700

Data Index: 704830 (Open Web Text)

Max Activating Token Index: 577