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

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

Neuron 1972 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.9386. Min Act: -0.1700

Data Index: 846980 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8917. Min Act: -0.1700

Data Index: 974283 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8604. Min Act: -0.1700

Data Index: 305906 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8604. Min Act: -0.1700

Data Index: 884712 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8448. Min Act: -0.1700

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8292. Min Act: -0.1700

Data Index: 412196 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8292. Min Act: -0.1700

Data Index: 1016009 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8604. Min Act: -0.1700

Data Index: 476266 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8448. Min Act: -0.1700

Data Index: 36814 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7822. Min Act: -0.1700

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7822. Min Act: -0.1700

Data Index: 1001284 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7666. Min Act: -0.1700

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.8292. Min Act: -0.1700

Data Index: 1074184 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7666. Min Act: -0.1700

Data Index: 373945 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 3.9386. Min Range: -3.9386

Max Act: 3.7979. Min Act: -0.1700

Data Index: 748077 (C4 (Web Text))

Max Activating Token Index: 426