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

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

Neuron 2587 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: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0002

Data Index: 908167 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0309. Min Act: -0.0002

Data Index: 591871 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0311. Min Act: -0.0002

Data Index: 192572 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1134019 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0290. Min Act: -0.0002

Data Index: 70741 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0291. Min Act: -0.0002

Data Index: 657175 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0298. Min Act: -0.0002

Data Index: 36553 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0286. Min Act: -0.0002

Data Index: 659061 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1125794 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1093433 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1039219 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1015952 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0277. Min Act: -0.0002

Data Index: 542596 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0268. Min Act: -0.0002

Data Index: 144377 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0247. Min Act: -0.0002

Data Index: 958090 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1213918 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0245. Min Act: -0.0002

Data Index: 974376 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0260. Min Act: -0.0002

Data Index: 847412 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0002

Data Index: 596294 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0255. Min Act: -0.0002

Data Index: 819422 (C4 (Web Text))

Max Activating Token Index: 331