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

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

Neuron 3829 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: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0003

Data Index: 876051 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1268374 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1030869 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0304. Min Act: -0.0004

Data Index: 582218 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1001253 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0003

Data Index: 646963 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0260. Min Act: -0.0003

Data Index: 92639 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0303. Min Act: -0.0003

Data Index: 522876 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0260. Min Act: -0.0003

Data Index: 636247 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0280. Min Act: -0.0003

Data Index: 874002 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0299. Min Act: -0.0003

Data Index: 769217 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0265. Min Act: -0.0003

Data Index: 818765 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0274. Min Act: -0.0003

Data Index: 880801 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0270. Min Act: -0.0003

Data Index: 279279 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1303920 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1458821 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0253. Min Act: -0.0004

Data Index: 104233 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0297. Min Act: -0.0003

Data Index: 61166 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0277. Min Act: -0.0003

Data Index: 704337 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0266. Min Act: -0.0003

Data Index: 774182 (C4 (Web Text))

Max Activating Token Index: 457