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

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

Neuron 3051 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: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0003

Data Index: 470413 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0324. Min Act: -0.0002

Data Index: 162550 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0335. Min Act: -0.0002

Data Index: 846648 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0325. Min Act: -0.0003

Data Index: 374713 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0322. Min Act: -0.0003

Data Index: 621194 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0303. Min Act: -0.0003

Data Index: 19289 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1055391 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1075364 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0292. Min Act: -0.0003

Data Index: 842174 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0295. Min Act: -0.0003

Data Index: 448869 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0301. Min Act: -0.0003

Data Index: 735814 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1166188 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0269. Min Act: -0.0003

Data Index: 504093 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1220716 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0295. Min Act: -0.0003

Data Index: 939038 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0286. Min Act: -0.0003

Data Index: 740845 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1180168 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0272. Min Act: -0.0003

Data Index: 511728 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0282. Min Act: -0.0003

Data Index: 726368 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0281. Min Act: -0.0003

Data Index: 807591 (C4 (Web Text))

Max Activating Token Index: 297