Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4731 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 694003 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0349. Min Act: -0.0002

Data Index: 499390 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0348. Min Act: -0.0002

Data Index: 14295 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0335. Min Act: -0.0002

Data Index: 48737 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0318. Min Act: -0.0002

Data Index: 891879 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0306. Min Act: -0.0002

Data Index: 606305 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1195532 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1534984 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0295. Min Act: -0.0002

Data Index: 694832 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1469972 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0291. Min Act: -0.0002

Data Index: 729574 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1347132 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0278. Min Act: -0.0002

Data Index: 712156 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0280. Min Act: -0.0002

Data Index: 541832 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0274. Min Act: -0.0002

Data Index: 175139 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0284. Min Act: -0.0002

Data Index: 486179 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0271. Min Act: -0.0002

Data Index: 766916 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1605646 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0273. Min Act: -0.0002

Data Index: 209594 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1026183 (C4 (Web Text))

Max Activating Token Index: 30