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

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

Neuron 1766 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1416119 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1487076 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1503586 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1625384 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1496165 (Python Code)

Max Activating Token Index: 466

Text #5

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1485952 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1528404 (Python Code)

Max Activating Token Index: 822

Text #7

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1640050 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1543984 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1618540 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1474974 (Python Code)

Max Activating Token Index: 854

Text #11

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1440382 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1397948 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1558546 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1603501 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1368452 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1453733 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1567965 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1484624 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.5359. Min Range: -0.5359

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1575558 (Python Code)

Max Activating Token Index: 768