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

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

Neuron 1142 in Layer 3

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: 0.0249. Min Act: -0.0001

Data Index: 462980 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1297202 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0235. Min Act: -0.0001

Data Index: 686651 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0224. Min Act: -0.0001

Data Index: 960216 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0212. Min Act: -0.0001

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1113096 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0228. Min Act: -0.0001

Data Index: 356364 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0215. Min Act: -0.0001

Data Index: 934471 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0214. Min Act: -0.0001

Data Index: 669362 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1163791 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0192. Min Act: -0.0001

Data Index: 1104249 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1128427 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1227506 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1357511 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1582031 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0214. Min Act: -0.0001

Data Index: 832638 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0202. Min Act: -0.0001

Data Index: 459430 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0200. Min Act: -0.0001

Data Index: 183084 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0205. Min Act: -0.0001

Data Index: 740628 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0249. Min Range: -0.0249

Max Act: 0.0187. Min Act: -0.0001

Data Index: 351435 (C4 (Web Text))

Max Activating Token Index: 95