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

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

Neuron 505 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1152192 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0001

Data Index: 186120 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1162. Min Act: -0.0001

Data Index: 65171 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1223. Min Act: -0.0001

Data Index: 585727 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1186. Min Act: -0.0001

Data Index: 701748 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1212. Min Act: -0.0001

Data Index: 990660 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1175. Min Act: -0.0001

Data Index: 18403 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1144. Min Act: -0.0001

Data Index: 31607 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1066. Min Act: -0.0001

Data Index: 643305 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1121. Min Act: -0.0001

Data Index: 49277 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1133221 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1165. Min Act: -0.0001

Data Index: 294998 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1130893 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1114. Min Act: -0.0001

Data Index: 6498 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1273768 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1090. Min Act: -0.0001

Data Index: 445664 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1355776 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1102. Min Act: -0.0001

Data Index: 201475 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1072. Min Act: -0.0001

Data Index: 43103 (C4 (Web Text))

Max Activating Token Index: 516