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

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

Neuron 348 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1088224 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0213. Min Act: -0.0003

Data Index: 363295 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0003

Data Index: 889977 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1121970 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1144077 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0186. Min Act: -0.0003

Data Index: 713341 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0190. Min Act: -0.0003

Data Index: 27704 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1154869 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0183. Min Act: -0.0003

Data Index: 937592 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0181. Min Act: -0.0003

Data Index: 317258 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1580503 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0178. Min Act: -0.0002

Data Index: 493726 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0182. Min Act: -0.0003

Data Index: 571648 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0180. Min Act: -0.0003

Data Index: 664849 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1599361 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0177. Min Act: -0.0003

Data Index: 845956 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0181. Min Act: -0.0003

Data Index: 986692 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0171. Min Act: -0.0003

Data Index: 872075 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0173. Min Act: -0.0003

Data Index: 798918 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0167. Min Act: -0.0002

Data Index: 800077 (C4 (Web Text))

Max Activating Token Index: 820