Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3594 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 873284 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0369. Min Act: -0.0003

Data Index: 801500 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0358. Min Act: -0.0003

Data Index: 928731 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0332. Min Act: -0.0004

Data Index: 694371 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0316. Min Act: -0.0003

Data Index: 907970 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0293. Min Act: -0.0003

Data Index: 247152 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1164968 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0293. Min Act: -0.0003

Data Index: 511220 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1057614 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1259461 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0270. Min Act: -0.0003

Data Index: 464479 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0290. Min Act: -0.0003

Data Index: 20729 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0290. Min Act: -0.0003

Data Index: 58587 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0276. Min Act: -0.0003

Data Index: 63898 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1130767 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0271. Min Act: -0.0003

Data Index: 283060 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0271. Min Act: -0.0004

Data Index: 1145613 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0270. Min Act: -0.0004

Data Index: 934439 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0263. Min Act: -0.0003

Data Index: 423432 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1069664 (C4 (Web Text))

Max Activating Token Index: 356