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

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

Neuron 1093 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 255814 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0258. Min Act: -0.0003

Data Index: 303930 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0257. Min Act: -0.0003

Data Index: 618203 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0241. Min Act: -0.0003

Data Index: 921430 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0235. Min Act: -0.0003

Data Index: 822052 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0230. Min Act: -0.0003

Data Index: 455291 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0227. Min Act: -0.0003

Data Index: 29770 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0228. Min Act: -0.0003

Data Index: 119324 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0224. Min Act: -0.0004

Data Index: 147681 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0224. Min Act: -0.0003

Data Index: 466608 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0228. Min Act: -0.0003

Data Index: 826439 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0230. Min Act: -0.0004

Data Index: 417659 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0221. Min Act: -0.0003

Data Index: 866121 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0223. Min Act: -0.0003

Data Index: 145600 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0223. Min Act: -0.0003

Data Index: 367665 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0222. Min Act: -0.0003

Data Index: 481124 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0219. Min Act: -0.0003

Data Index: 446529 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0220. Min Act: -0.0004

Data Index: 456157 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0217. Min Act: -0.0003

Data Index: 316020 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0221. Min Act: -0.0004

Data Index: 131004 (C4 (Web Text))

Max Activating Token Index: 584