Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1586517 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0266. Min Act: -0.0006

Data Index: 1652141 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0236. Min Act: -0.0006

Data Index: 813931 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0232. Min Act: -0.0006

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0222. Min Act: -0.0006

Data Index: 195636 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0214. Min Act: -0.0006

Data Index: 379059 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0228. Min Act: -0.0006

Data Index: 458329 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0231. Min Act: -0.0006

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0212. Min Act: -0.0006

Data Index: 39662 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1561735 (Python Code)

Max Activating Token Index: 414

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0222. Min Act: -0.0006

Data Index: 169331 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1086987 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1135873 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0225. Min Act: -0.0006

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0220. Min Act: -0.0006

Data Index: 1326556 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0223. Min Act: -0.0006

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1378902 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0221. Min Act: -0.0006

Data Index: 391804 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1095786 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0215. Min Act: -0.0006

Data Index: 105250 (C4 (Web Text))

Max Activating Token Index: 409