Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1366 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.9620. Min Act: -0.1700

Data Index: 536641 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8995. Min Act: -0.1700

Data Index: 120190 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8682. Min Act: -0.1700

Data Index: 1309497 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8995. Min Act: -0.1700

Data Index: 1157823 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1069929 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8682. Min Act: -0.1700

Data Index: 976524 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8057. Min Act: -0.1700

Data Index: 568575 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8057. Min Act: -0.1700

Data Index: 555519 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.8057. Min Act: -0.1700

Data Index: 750698 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7118. Min Act: -0.1700

Data Index: 315859 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7431. Min Act: -0.1700

Data Index: 609982 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7431. Min Act: -0.1700

Data Index: 272273 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7431. Min Act: -0.1700

Data Index: 234546 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7744. Min Act: -0.1700

Data Index: 712426 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7431. Min Act: -0.1700

Data Index: 18214 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7118. Min Act: -0.1700

Data Index: 2574 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7431. Min Act: -0.1700

Data Index: 1113409 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.6805. Min Act: -0.1700

Data Index: 13821 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.7118. Min Act: -0.1700

Data Index: 799728 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.9620. Min Range: -3.9620

Max Act: 3.6805. Min Act: -0.1700

Data Index: 82646 (C4 (Web Text))

Max Activating Token Index: 23