Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1006 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0005

Data Index: 776106 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0315. Min Act: -0.0006

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0328. Min Act: -0.0005

Data Index: 1162677 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0328. Min Act: -0.0006

Data Index: 671337 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0324. Min Act: -0.0006

Data Index: 604127 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0306. Min Act: -0.0006

Data Index: 677677 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0293. Min Act: -0.0006

Data Index: 189220 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1163432 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0323. Min Act: -0.0005

Data Index: 868998 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0294. Min Act: -0.0006

Data Index: 919850 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0299. Min Act: -0.0006

Data Index: 923632 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1319983 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0288. Min Act: -0.0005

Data Index: 760724 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0294. Min Act: -0.0006

Data Index: 540651 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0279. Min Act: -0.0006

Data Index: 270025 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1127299 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0297. Min Act: -0.0006

Data Index: 866453 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0289. Min Act: -0.0005

Data Index: 443665 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1288143 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1119719 (C4 (Web Text))

Max Activating Token Index: 750