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

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

Neuron 1054 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: 5.0805. Min Range: -5.0805

Max Act: 5.0805. Min Act: -0.1700

Data Index: 591345 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 5.0805. Min Range: -5.0805

Max Act: 5.0492. Min Act: -0.1700

Data Index: 1103892 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.8930. Min Act: -0.1699

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.8930. Min Act: -0.1700

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.9242. Min Act: -0.1700

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.9242. Min Act: -0.1699

Data Index: 961135 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.9242. Min Act: -0.1700

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.8617. Min Act: -0.1700

Data Index: 926126 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.8617. Min Act: -0.1700

Data Index: 994115 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.8305. Min Act: -0.1700

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7992. Min Act: -0.1700

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7992. Min Act: -0.1700

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7992. Min Act: -0.1700

Data Index: 614262 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7680. Min Act: -0.1700

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7367. Min Act: -0.1700

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7680. Min Act: -0.1699

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7367. Min Act: -0.1700

Data Index: 43559 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7367. Min Act: -0.1700

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7367. Min Act: -0.1700

Data Index: 973233 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 5.0805. Min Range: -5.0805

Max Act: 4.7367. Min Act: -0.1699

Data Index: 781495 (C4 (Web Text))

Max Activating Token Index: 615