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

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

Neuron 3967 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 425285 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1179898 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0003

Data Index: 452044 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0269. Min Act: -0.0003

Data Index: 32643 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0263. Min Act: -0.0002

Data Index: 677843 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0263. Min Act: -0.0003

Data Index: 206791 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0257. Min Act: -0.0003

Data Index: 281828 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1335328 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0239. Min Act: -0.0003

Data Index: 603846 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0237. Min Act: -0.0003

Data Index: 968436 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0003

Data Index: 174352 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0002

Data Index: 808963 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0237. Min Act: -0.0003

Data Index: 507397 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0238. Min Act: -0.0003

Data Index: 788969 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1296611 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0241. Min Act: -0.0003

Data Index: 776820 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0226. Min Act: -0.0003

Data Index: 387890 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1220828 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0229. Min Act: -0.0003

Data Index: 970608 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0229. Min Act: -0.0003

Data Index: 128380 (C4 (Web Text))

Max Activating Token Index: 767