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

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

Neuron 4669 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: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0002

Data Index: 756297 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0227. Min Act: -0.0002

Data Index: 229473 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0226. Min Act: -0.0002

Data Index: 176076 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0225. Min Act: -0.0002

Data Index: 262659 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0224. Min Act: -0.0002

Data Index: 460987 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0225. Min Act: -0.0002

Data Index: 521286 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1299087 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0219. Min Act: -0.0002

Data Index: 72883 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0219. Min Act: -0.0002

Data Index: 804584 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0216. Min Act: -0.0002

Data Index: 301086 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1206553 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1149660 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1000902 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0214. Min Act: -0.0002

Data Index: 936522 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0212. Min Act: -0.0002

Data Index: 337100 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0212. Min Act: -0.0002

Data Index: 105710 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0207. Min Act: -0.0002

Data Index: 235085 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0002

Data Index: 844141 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0210. Min Act: -0.0002

Data Index: 302879 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0209. Min Act: -0.0002

Data Index: 31095 (C4 (Web Text))

Max Activating Token Index: 38