Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1854 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.6446. Min Act: -0.1700

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.6134. Min Act: -0.1700

Data Index: 641851 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.6446. Min Act: -0.1700

Data Index: 237767 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4884. Min Act: -0.1700

Data Index: 1076647 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4884. Min Act: -0.1700

Data Index: 598629 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.5196. Min Act: -0.1700

Data Index: 985888 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.5821. Min Act: -0.1700

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.5196. Min Act: -0.1700

Data Index: 1285991 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.5821. Min Act: -0.1700

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4571. Min Act: -0.1700

Data Index: 483389 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4259. Min Act: -0.1700

Data Index: 883557 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4259. Min Act: -0.1700

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4884. Min Act: -0.1700

Data Index: 124191 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4571. Min Act: -0.1700

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.3946. Min Act: -0.1700

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.3321. Min Act: -0.1700

Data Index: 1038543 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4571. Min Act: -0.1700

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.3946. Min Act: -0.1700

Data Index: 1294697 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.4259. Min Act: -0.1700

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.6446. Min Range: -5.6446

Max Act: 5.3634. Min Act: -0.1700

Data Index: 1248815 (C4 (Web Text))

Max Activating Token Index: 746