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

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

Neuron 4070 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: 0.0251. Min Range: -0.0251

Max Act: 0.0247. Min Act: -0.0002

Data Index: 867974 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1340956 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0244. Min Act: -0.0002

Data Index: 890048 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0240. Min Act: -0.0002

Data Index: 287175 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1148684 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0243. Min Act: -0.0002

Data Index: 965576 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1262379 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0235. Min Act: -0.0002

Data Index: 689332 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0237. Min Act: -0.0002

Data Index: 369306 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1546580 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0229. Min Act: -0.0002

Data Index: 867204 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0228. Min Act: -0.0002

Data Index: 679797 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0225. Min Act: -0.0002

Data Index: 655454 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1233263 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1211010 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0002

Data Index: 66070 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0223. Min Act: -0.0002

Data Index: 391285 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1584492 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0218. Min Act: -0.0002

Data Index: 820748 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0002

Data Index: 95151 (C4 (Web Text))

Max Activating Token Index: 12