Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.5108. Min Act: -0.0002

Data Index: 399293 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.5805. Min Act: -0.0002

Data Index: 470214 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.5041. Min Act: -0.0002

Data Index: 521437 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4843. Min Act: -0.0002

Data Index: 1191068 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4836. Min Act: -0.0002

Data Index: 8235 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4396. Min Act: -0.0002

Data Index: 604781 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4845. Min Act: -0.0002

Data Index: 376098 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4673. Min Act: -0.0002

Data Index: 1071177 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4358. Min Act: -0.0002

Data Index: 1182907 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4172. Min Act: -0.0002

Data Index: 142164 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4442. Min Act: -0.0002

Data Index: 1146678 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4566. Min Act: -0.0002

Data Index: 815570 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4722. Min Act: -0.0002

Data Index: 881240 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4687. Min Act: -0.0002

Data Index: 1329013 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.5363. Min Act: -0.0002

Data Index: 766546 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4902. Min Act: -0.0002

Data Index: 136262 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4523. Min Act: -0.0002

Data Index: 1094205 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4664. Min Act: -0.0002

Data Index: 550566 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4625. Min Act: -0.0002

Data Index: 789297 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.5805. Min Range: -0.5805

Max Act: 0.4568. Min Act: -0.0002

Data Index: 1309716 (C4 (Web Text))

Max Activating Token Index: 338