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

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

Neuron 345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0002

Data Index: 641024 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0255. Min Act: -0.0002

Data Index: 855530 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0253. Min Act: -0.0002

Data Index: 547948 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0241. Min Act: -0.0002

Data Index: 108844 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0002

Data Index: 123823 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0213. Min Act: -0.0002

Data Index: 280700 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0214. Min Act: -0.0002

Data Index: 68645 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0002

Data Index: 138150 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0214. Min Act: -0.0002

Data Index: 239222 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1110430 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0215. Min Act: -0.0002

Data Index: 289091 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1352030 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0200. Min Act: -0.0002

Data Index: 575470 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1376878 (Python Code)

Max Activating Token Index: 361

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1290767 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0190. Min Act: -0.0002

Data Index: 733441 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0189. Min Act: -0.0002

Data Index: 343569 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0185. Min Act: -0.0002

Data Index: 743183 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0188. Min Act: -0.0002

Data Index: 926242 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0191. Min Act: -0.0002

Data Index: 842174 (C4 (Web Text))

Max Activating Token Index: 539