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

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

Neuron 2678 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: 0.0229. Min Range: -0.0229

Max Act: 0.0223. Min Act: -0.0002

Data Index: 398371 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1533971 (Python Code)

Max Activating Token Index: 442

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1391867 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0002

Data Index: 870522 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1178398 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1417010 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0185. Min Act: -0.0002

Data Index: 334741 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0189. Min Act: -0.0002

Data Index: 944848 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1296212 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0165. Min Act: -0.0002

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1504280 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0170. Min Act: -0.0002

Data Index: 235633 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0163. Min Act: -0.0002

Data Index: 757205 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0160. Min Act: -0.0002

Data Index: 670326 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0156. Min Act: -0.0002

Data Index: 409400 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0159. Min Act: -0.0002

Data Index: 418467 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1533839 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1233801 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0150. Min Act: -0.0002

Data Index: 804732 (C4 (Web Text))

Max Activating Token Index: 213