Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3700 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1285090 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1263424 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0313. Min Act: -0.0003

Data Index: 129420 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1281723 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1623480 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1453404 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1493274 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0229. Min Act: -0.0003

Data Index: 818726 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1556269 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0186. Min Act: -0.0003

Data Index: 479381 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1527204 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1376027 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1396148 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1463648 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1532166 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1626124 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1585963 (Python Code)

Max Activating Token Index: 607

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1533988 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1505649 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1621799 (Python Code)

Max Activating Token Index: 329