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

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

Neuron 1115 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0000

Data Index: 1093997 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0206. Min Act: -0.0000

Data Index: 1297574 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1567302 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0205. Min Act: -0.0000

Data Index: 1198865 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1480690 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0204. Min Act: -0.0000

Data Index: 859743 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0183. Min Act: -0.0000

Data Index: 396187 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0189. Min Act: -0.0000

Data Index: 836980 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0191. Min Act: -0.0000

Data Index: 419490 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0181. Min Act: -0.0000

Data Index: 1468622 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0179. Min Act: -0.0000

Data Index: 63066 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0164. Min Act: -0.0000

Data Index: 1283382 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1177625 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0180. Min Act: -0.0000

Data Index: 914075 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0170. Min Act: -0.0000

Data Index: 1565092 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0170. Min Act: -0.0000

Data Index: 488643 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0168. Min Act: -0.0000

Data Index: 9024 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0183. Min Act: -0.0000

Data Index: 964688 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1163390 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0171. Min Act: -0.0000

Data Index: 162195 (C4 (Web Text))

Max Activating Token Index: 959