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

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

Neuron 2122 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: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0003

Data Index: 910863 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1426760 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0263. Min Act: -0.0003

Data Index: 551342 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1375879 (Python Code)

Max Activating Token Index: 656

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1104018 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0231. Min Act: -0.0003

Data Index: 269846 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1290534 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0003

Data Index: 964952 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0003

Data Index: 157240 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1599889 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0219. Min Act: -0.0003

Data Index: 888268 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1018639 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0003

Data Index: 616554 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0217. Min Act: -0.0003

Data Index: 368882 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1531720 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0220. Min Act: -0.0003

Data Index: 327621 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1489584 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1468544 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0209. Min Act: -0.0003

Data Index: 125214 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0215. Min Act: -0.0003

Data Index: 531394 (C4 (Web Text))

Max Activating Token Index: 805