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

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

Neuron 137 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: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0002

Data Index: 325864 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1064847 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0203. Min Act: -0.0002

Data Index: 740043 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0184. Min Act: -0.0002

Data Index: 672913 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1132663 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0184. Min Act: -0.0002

Data Index: 674728 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0184. Min Act: -0.0002

Data Index: 970914 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1338699 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0193. Min Act: -0.0002

Data Index: 476704 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1376813 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0168. Min Act: -0.0002

Data Index: 881387 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1337371 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0159. Min Act: -0.0002

Data Index: 291193 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1279843 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0152. Min Act: -0.0002

Data Index: 280652 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0175. Min Act: -0.0002

Data Index: 160339 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0171. Min Act: -0.0002

Data Index: 916417 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0169. Min Act: -0.0002

Data Index: 690055 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1195781 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1463706 (Python Code)

Max Activating Token Index: 510