Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2959 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.8290. Min Act: -0.0000

Data Index: 1436627 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7461. Min Act: -0.0000

Data Index: 1738157 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.8701. Min Act: -0.0000

Data Index: 692661 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.8972. Min Act: -0.0000

Data Index: 1551090 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6715. Min Act: -0.0000

Data Index: 1002552 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.4085. Min Act: -0.0000

Data Index: 1024113 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.7266. Min Act: -0.0000

Data Index: 1923752 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.4759. Min Act: -0.0000

Data Index: 1450253 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.3086. Min Act: -0.0000

Data Index: 19925 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.6033. Min Act: -0.0000

Data Index: 507763 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.3343. Min Act: -0.0000

Data Index: 1347443 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.3385. Min Act: -0.0000

Data Index: 934410 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.3508. Min Act: -0.0000

Data Index: 990006 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1851065 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.1062. Min Act: -0.0000

Data Index: 1371122 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.2026. Min Act: -0.0000

Data Index: 1248380 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.1589. Min Act: -0.0000

Data Index: 1415815 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.1195. Min Act: -0.0000

Data Index: 1512688 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.1818. Min Act: -0.0000

Data Index: 1910207 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 3.8972. Min Range: -3.8972

Max Act: 3.0200. Min Act: -0.0000

Data Index: 46511 (The Pile)

Max Activating Token Index: 633