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

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

Neuron 3352 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3775. Min Act: -0.0001

Data Index: 807403 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.3206. Min Act: -0.0001

Data Index: 666148 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2789. Min Act: -0.0001

Data Index: 46838 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1193079 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1311630 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1234844 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2374. Min Act: -0.0001

Data Index: 747728 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2252. Min Act: -0.0001

Data Index: 330752 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2332. Min Act: -0.0001

Data Index: 835278 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2133. Min Act: -0.0001

Data Index: 943365 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2272. Min Act: -0.0001

Data Index: 534640 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2248. Min Act: -0.0001

Data Index: 279795 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2363. Min Act: -0.0001

Data Index: 429275 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2452. Min Act: -0.0001

Data Index: 1114690 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2061. Min Act: -0.0001

Data Index: 645277 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2089. Min Act: -0.0001

Data Index: 428744 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2102. Min Act: -0.0001

Data Index: 722575 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1131372 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1083232 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.3775. Min Range: -0.3775

Max Act: 0.2042. Min Act: -0.0001

Data Index: 944584 (C4 (Web Text))

Max Activating Token Index: 670