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

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

Neuron 3795 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: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0003

Data Index: 751436 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1281038 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0327. Min Act: -0.0003

Data Index: 81433 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0320. Min Act: -0.0003

Data Index: 418307 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0326. Min Act: -0.0003

Data Index: 519045 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0331. Min Act: -0.0003

Data Index: 635050 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0319. Min Act: -0.0002

Data Index: 23358 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0317. Min Act: -0.0003

Data Index: 15468 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0313. Min Act: -0.0003

Data Index: 43378 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1126494 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0305. Min Act: -0.0003

Data Index: 793098 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0298. Min Act: -0.0003

Data Index: 637691 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1011560 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1082360 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0295. Min Act: -0.0003

Data Index: 768829 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0294. Min Act: -0.0003

Data Index: 580195 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0293. Min Act: -0.0003

Data Index: 795496 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0287. Min Act: -0.0003

Data Index: 318401 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0297. Min Act: -0.0002

Data Index: 56758 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1520651 (Python Code)

Max Activating Token Index: 162