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

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

Neuron 4562 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: 0.0376. Min Range: -0.0376

Max Act: 0.0376. Min Act: -0.0002

Data Index: 932765 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1055092 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0269. Min Act: -0.0002

Data Index: 563932 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1193336 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0275. Min Act: -0.0002

Data Index: 900136 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0252. Min Act: -0.0002

Data Index: 264911 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0252. Min Act: -0.0002

Data Index: 38828 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0249. Min Act: -0.0002

Data Index: 962063 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0253. Min Act: -0.0002

Data Index: 660354 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0249. Min Act: -0.0002

Data Index: 196315 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0246. Min Act: -0.0002

Data Index: 397784 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0247. Min Act: -0.0002

Data Index: 153235 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0248. Min Act: -0.0002

Data Index: 864641 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1131425 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0231. Min Act: -0.0002

Data Index: 875197 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1026438 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0223. Min Act: -0.0002

Data Index: 316368 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0223. Min Act: -0.0002

Data Index: 93884 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0226. Min Act: -0.0002

Data Index: 462693 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0376. Min Range: -0.0376

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1326765 (C4 (Web Text))

Max Activating Token Index: 328