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

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

Neuron 3810 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: 0.0309. Min Range: -0.0309

Max Act: 0.0284. Min Act: -0.0003

Data Index: 824960 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0003

Data Index: 971085 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0296. Min Act: -0.0003

Data Index: 389903 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1466138 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0003

Data Index: 448464 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0293. Min Act: -0.0003

Data Index: 292868 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0268. Min Act: -0.0003

Data Index: 724727 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1445899 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1366272 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0003

Data Index: 654139 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0266. Min Act: -0.0003

Data Index: 458970 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1405109 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0003

Data Index: 736106 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0300. Min Act: -0.0004

Data Index: 281289 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0302. Min Act: -0.0003

Data Index: 571032 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0003

Data Index: 335633 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1083238 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1296233 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0003

Data Index: 643404 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0244. Min Act: -0.0003

Data Index: 518409 (C4 (Web Text))

Max Activating Token Index: 601