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

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

Neuron 3401 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: 0.2720. Min Range: -0.2720

Max Act: 0.2660. Min Act: -0.0002

Data Index: 829155 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2720. Min Act: -0.0002

Data Index: 1197076 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2430. Min Act: -0.0002

Data Index: 1047059 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2354. Min Act: -0.0002

Data Index: 1303632 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2460. Min Act: -0.0002

Data Index: 539872 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2527. Min Act: -0.0002

Data Index: 549533 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2427. Min Act: -0.0002

Data Index: 1330822 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2455. Min Act: -0.0002

Data Index: 1330835 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2638. Min Act: -0.0002

Data Index: 1309504 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2572. Min Act: -0.0002

Data Index: 1212004 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2466. Min Act: -0.0002

Data Index: 892597 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2373. Min Act: -0.0002

Data Index: 657535 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2345. Min Act: -0.0002

Data Index: 338156 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2407. Min Act: -0.0002

Data Index: 391482 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2222. Min Act: -0.0002

Data Index: 1026045 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2282. Min Act: -0.0002

Data Index: 767121 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2292. Min Act: -0.0002

Data Index: 521811 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1974. Min Act: -0.0002

Data Index: 53305 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2269. Min Act: -0.0002

Data Index: 1122138 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2179. Min Act: -0.0002

Data Index: 579519 (C4 (Web Text))

Max Activating Token Index: 599