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

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

Neuron 2558 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0240. Min Act: -0.0003

Data Index: 692498 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1354260 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0218. Min Act: -0.0003

Data Index: 558025 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1072838 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0212. Min Act: -0.0003

Data Index: 69895 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0201. Min Act: -0.0003

Data Index: 231330 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0205. Min Act: -0.0003

Data Index: 423465 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1231346 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0209. Min Act: -0.0003

Data Index: 267052 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0204. Min Act: -0.0003

Data Index: 555673 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1151985 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0198. Min Act: -0.0003

Data Index: 105175 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1089193 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0201. Min Act: -0.0003

Data Index: 126262 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1285195 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0200. Min Act: -0.0003

Data Index: 434599 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0199. Min Act: -0.0003

Data Index: 751624 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0187. Min Act: -0.0003

Data Index: 105360 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0194. Min Act: -0.0003

Data Index: 398909 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0197. Min Act: -0.0003

Data Index: 924824 (C4 (Web Text))

Max Activating Token Index: 196