Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2149 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0271. Min Act: -0.0004

Data Index: 1648491 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1480405 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1460997 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1401350 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1599551 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0256. Min Act: -0.0004

Data Index: 1463877 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1553508 (Python Code)

Max Activating Token Index: 487

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1525078 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1479458 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0211. Min Act: -0.0004

Data Index: 1517084 (Python Code)

Max Activating Token Index: 545

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1641831 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1413264 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1384161 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1645675 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1518790 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1376293 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1548992 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1400621 (Python Code)

Max Activating Token Index: 269

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1519098 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1467725 (Python Code)

Max Activating Token Index: 56