Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1058033 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1341427 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1138848 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1403829 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0242. Min Act: -0.0006

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0006

Data Index: 85484 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0224. Min Act: -0.0006

Data Index: 413949 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0222. Min Act: -0.0006

Data Index: 218519 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0006

Data Index: 680578 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0225. Min Act: -0.0006

Data Index: 515372 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0206. Min Act: -0.0006

Data Index: 278965 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0211. Min Act: -0.0006

Data Index: 1161311 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0006

Data Index: 59542 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1166868 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0226. Min Act: -0.0006

Data Index: 537718 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1201679 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1111078 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0210. Min Act: -0.0006

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0219. Min Act: -0.0006

Data Index: 866010 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0204. Min Act: -0.0006

Data Index: 268519 (C4 (Web Text))

Max Activating Token Index: 155