Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 868 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1904825 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1247785 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 1.1025. Min Range: -1.1025

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1449319 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.9570. Min Act: -0.0000

Data Index: 985106 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1738042 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8821. Min Act: -0.0000

Data Index: 88695 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1905290 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1481311 (The Pile)

Max Activating Token Index: 209

Text #8

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7421. Min Act: -0.0000

Data Index: 583714 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7825. Min Act: -0.0000

Data Index: 526275 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7661. Min Act: -0.0000

Data Index: 250910 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1845791 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7551. Min Act: -0.0000

Data Index: 934144 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1444001 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6604. Min Act: -0.0000

Data Index: 362893 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1093708 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1542656 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6394. Min Act: -0.0000

Data Index: 817081 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1763277 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.1025. Min Range: -1.1025

Max Act: 0.6935. Min Act: 0.0000

Data Index: 430296 (The Pile)

Max Activating Token Index: 324