Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1925 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1266293 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0286. Min Act: -0.0003

Data Index: 196457 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1651826 (Python Code)

Max Activating Token Index: 274

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0299. Min Act: -0.0003

Data Index: 330968 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0277. Min Act: -0.0004

Data Index: 308696 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1016278 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0259. Min Act: -0.0003

Data Index: 722840 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0242. Min Act: -0.0003

Data Index: 135585 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0275. Min Act: -0.0003

Data Index: 414906 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1616736 (Python Code)

Max Activating Token Index: 1017

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0273. Min Act: -0.0003

Data Index: 233103 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0235. Min Act: -0.0003

Data Index: 71181 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0254. Min Act: -0.0003

Data Index: 919431 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0264. Min Act: -0.0003

Data Index: 677943 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0237. Min Act: -0.0003

Data Index: 196211 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0239. Min Act: -0.0003

Data Index: 20663 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0187. Min Act: -0.0003

Data Index: 383388 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1519978 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0266. Min Act: -0.0003

Data Index: 382750 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1054662 (C4 (Web Text))

Max Activating Token Index: 956