Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1721 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1483906 (Python Code)

Max Activating Token Index: 623

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0246. Min Act: -0.0006

Data Index: 885231 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1640705 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0219. Min Act: -0.0006

Data Index: 170995 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1154305 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1331176 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1239505 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1369912 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0208. Min Act: -0.0006

Data Index: 527509 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0227. Min Act: -0.0006

Data Index: 735266 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0217. Min Act: -0.0006

Data Index: 4822 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0194. Min Act: -0.0006

Data Index: 778478 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1205072 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1240107 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1156991 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0209. Min Act: -0.0006

Data Index: 869018 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1247667 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0204. Min Act: -0.0005

Data Index: 586758 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0207. Min Act: -0.0006

Data Index: 243718 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0211. Min Act: -0.0006

Data Index: 406069 (C4 (Web Text))

Max Activating Token Index: 604