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

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

Neuron 1601 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0234. Min Act: -0.0002

Data Index: 596983 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0002

Data Index: 432313 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0235. Min Act: -0.0002

Data Index: 9715 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1513510 (Python Code)

Max Activating Token Index: 558

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1014349 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0187. Min Act: -0.0002

Data Index: 315476 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1423547 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1335205 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0179. Min Act: -0.0002

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1580473 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1410507 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1602101 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0166. Min Act: -0.0002

Data Index: 163755 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0166. Min Act: -0.0002

Data Index: 322392 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0174. Min Act: -0.0002

Data Index: 49597 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1442923 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1556532 (Python Code)

Max Activating Token Index: 95

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1447545 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1477057 (Python Code)

Max Activating Token Index: 89