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

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

Neuron 1026 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: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1141464 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0251. Min Act: -0.0003

Data Index: 330228 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1260914 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1088150 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1274030 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0193. Min Act: -0.0003

Data Index: 210249 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0194. Min Act: -0.0002

Data Index: 745876 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0201. Min Act: -0.0002

Data Index: 779247 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1102673 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1036794 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0191. Min Act: -0.0003

Data Index: 148890 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0184. Min Act: -0.0002

Data Index: 628166 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0183. Min Act: -0.0003

Data Index: 948875 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1646437 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1498030 (Python Code)

Max Activating Token Index: 550

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0166. Min Act: -0.0003

Data Index: 106763 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1239578 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1153345 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0160. Min Act: -0.0003

Data Index: 86135 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1284047 (C4 (Web Text))

Max Activating Token Index: 719