Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.6344. Min Act: -0.1700

Data Index: 1246982 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2907. Min Act: -0.1700

Data Index: 399722 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.1344. Min Act: -0.1700

Data Index: 1062745 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.9782. Min Act: -0.1700

Data Index: 470341 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.9469. Min Act: -0.1699

Data Index: 1350725 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.9469. Min Act: -0.1700

Data Index: 583927 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.9469. Min Act: -0.1699

Data Index: 364736 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8532. Min Act: -0.1700

Data Index: 461893 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.9157. Min Act: -0.1696

Data Index: 861324 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8532. Min Act: -0.1700

Data Index: 1190635 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8219. Min Act: -0.1698

Data Index: 914314 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8532. Min Act: -0.1700

Data Index: 591175 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8532. Min Act: -0.1699

Data Index: 43189 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8219. Min Act: -0.1700

Data Index: 89528 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8219. Min Act: -0.1699

Data Index: 61629 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8219. Min Act: -0.1700

Data Index: 633711 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.7594. Min Act: -0.1700

Data Index: 208555 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8219. Min Act: -0.1700

Data Index: 317013 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.8532. Min Act: -0.1699

Data Index: 299372 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 5.6344. Min Range: -5.6344

Max Act: 4.7907. Min Act: -0.1700

Data Index: 420194 (C4 (Web Text))

Max Activating Token Index: 332