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

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

Neuron 1319 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: 3.7331. Min Range: -3.7331

Max Act: 3.7331. Min Act: -0.1700

Data Index: 343854 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.7331. Min Act: -0.1700

Data Index: 493682 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.7018. Min Act: -0.1700

Data Index: 929164 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.6705. Min Act: -0.1700

Data Index: 653977 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.6079. Min Act: -0.1700

Data Index: 339785 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.6079. Min Act: -0.1700

Data Index: 279420 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5610. Min Act: -0.1700

Data Index: 150687 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5610. Min Act: -0.1700

Data Index: 485695 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.6079. Min Act: -0.1700

Data Index: 512634 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.6392. Min Act: -0.1700

Data Index: 1047496 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5766. Min Act: -0.1700

Data Index: 17168 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5766. Min Act: -0.1700

Data Index: 990173 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5296. Min Act: -0.1700

Data Index: 1125132 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5453. Min Act: -0.1700

Data Index: 188840 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5296. Min Act: -0.1700

Data Index: 262679 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5453. Min Act: -0.1700

Data Index: 541974 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5453. Min Act: -0.1700

Data Index: 716415 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5453. Min Act: -0.1700

Data Index: 629587 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5296. Min Act: -0.1700

Data Index: 793311 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 3.7331. Min Range: -3.7331

Max Act: 3.5140. Min Act: -0.1700

Data Index: 809989 (C4 (Web Text))

Max Activating Token Index: 379