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

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

Neuron 2539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0000

Data Index: 155888 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0362. Min Act: -0.0000

Data Index: 423699 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1326619 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0302. Min Act: -0.0000

Data Index: 524734 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1562322 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0307. Min Act: -0.0000

Data Index: 1050384 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1443369 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0279. Min Act: -0.0000

Data Index: 115166 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0277. Min Act: -0.0000

Data Index: 388326 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0280. Min Act: -0.0000

Data Index: 8696 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1401176 (Python Code)

Max Activating Token Index: 949

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0268. Min Act: -0.0000

Data Index: 819728 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1478244 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1275155 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0258. Min Act: -0.0000

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0247. Min Act: -0.0000

Data Index: 914705 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1512047 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0236. Min Act: -0.0001

Data Index: 881252 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0237. Min Act: -0.0000

Data Index: 196720 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0228. Min Act: -0.0000

Data Index: 87546 (C4 (Web Text))

Max Activating Token Index: 435