Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3396 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0248. Min Act: -0.0002

Data Index: 985441 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1072245 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0249. Min Act: -0.0002

Data Index: 980832 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0244. Min Act: -0.0002

Data Index: 823378 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0236. Min Act: -0.0002

Data Index: 462431 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0241. Min Act: -0.0002

Data Index: 814994 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0240. Min Act: -0.0002

Data Index: 343389 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1357032 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1073141 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1110183 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0234. Min Act: -0.0002

Data Index: 91957 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0238. Min Act: -0.0002

Data Index: 104839 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0232. Min Act: -0.0002

Data Index: 931587 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0232. Min Act: -0.0002

Data Index: 717225 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0227. Min Act: -0.0002

Data Index: 516611 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1002268 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0227. Min Act: -0.0002

Data Index: 494523 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0227. Min Act: -0.0002

Data Index: 843222 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1310895 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1038066 (C4 (Web Text))

Max Activating Token Index: 35