Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0000

Data Index: 12583 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1490125 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1222. Min Act: -0.0000

Data Index: 411288 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1227. Min Act: -0.0000

Data Index: 701782 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1178. Min Act: -0.0000

Data Index: 27674 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1155. Min Act: -0.0000

Data Index: 989924 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1200. Min Act: -0.0000

Data Index: 414220 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1067. Min Act: -0.0000

Data Index: 94517 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0999. Min Act: -0.0000

Data Index: 302750 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1061. Min Act: -0.0000

Data Index: 918102 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1078. Min Act: -0.0000

Data Index: 520579 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1002. Min Act: -0.0000

Data Index: 997029 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0977. Min Act: -0.0000

Data Index: 951326 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1177. Min Act: -0.0000

Data Index: 827305 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1021. Min Act: -0.0000

Data Index: 501763 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0948. Min Act: -0.0000

Data Index: 318824 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0959. Min Act: -0.0000

Data Index: 601289 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0939. Min Act: -0.0000

Data Index: 182868 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0938. Min Act: -0.0000

Data Index: 773629 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0932. Min Act: -0.0000

Data Index: 340259 (C4 (Web Text))

Max Activating Token Index: 501