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

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

Neuron 5870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0001

Data Index: 40267 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0360. Min Act: -0.0001

Data Index: 166869 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1053548 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0361. Min Act: -0.0001

Data Index: 610108 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0343. Min Act: -0.0001

Data Index: 851547 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0350. Min Act: -0.0001

Data Index: 341868 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0337. Min Act: -0.0001

Data Index: 94487 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0352. Min Act: -0.0001

Data Index: 856491 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0336. Min Act: -0.0001

Data Index: 822600 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0329. Min Act: -0.0001

Data Index: 257234 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0341. Min Act: -0.0001

Data Index: 426179 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0329. Min Act: -0.0001

Data Index: 810045 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0342. Min Act: -0.0001

Data Index: 378137 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0321. Min Act: -0.0001

Data Index: 450379 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0330. Min Act: -0.0001

Data Index: 81597 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0314. Min Act: -0.0001

Data Index: 576855 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0304. Min Act: -0.0001

Data Index: 737158 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0321. Min Act: -0.0001

Data Index: 779540 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1040779 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0297. Min Act: -0.0001

Data Index: 851727 (C4 (Web Text))

Max Activating Token Index: 870