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

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

Neuron 3220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0002

Data Index: 690587 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0300. Min Act: -0.0002

Data Index: 758755 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0291. Min Act: -0.0002

Data Index: 253508 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0290. Min Act: -0.0002

Data Index: 890715 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0288. Min Act: -0.0002

Data Index: 768195 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0286. Min Act: -0.0002

Data Index: 125614 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0282. Min Act: -0.0002

Data Index: 579033 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1222811 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0277. Min Act: -0.0002

Data Index: 811745 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1296364 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1147573 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0276. Min Act: -0.0002

Data Index: 45755 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1252839 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1252824 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0267. Min Act: -0.0002

Data Index: 372465 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1194694 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1202286 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1258361 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0266. Min Act: -0.0002

Data Index: 428390 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0265. Min Act: -0.0002

Data Index: 733440 (C4 (Web Text))

Max Activating Token Index: 175