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

Dataset: The Pile

Neuron 3207 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: 3.6844. Min Range: -3.6844

Max Act: 3.6844. Min Act: -0.0000

Data Index: 1718777 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.1017. Min Act: -0.0000

Data Index: 1597051 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.8766. Min Act: -0.0000

Data Index: 1387267 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.6263. Min Act: -0.0000

Data Index: 1962641 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1357033 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1497089 (The Pile)

Max Activating Token Index: 637

Text #6

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.4719. Min Act: -0.0000

Data Index: 1815261 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.4518. Min Act: -0.0000

Data Index: 500852 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.3952. Min Act: -0.0000

Data Index: 1355965 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.1383. Min Act: -0.0000

Data Index: 644675 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.3672. Min Act: -0.0000

Data Index: 889142 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.3183. Min Act: -0.0000

Data Index: 1548565 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.2873. Min Act: -0.0000

Data Index: 1760596 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.2712. Min Act: -0.0000

Data Index: 1141920 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.2439. Min Act: -0.0000

Data Index: 1041930 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1599300 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.2671. Min Act: -0.0000

Data Index: 1739968 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.1365. Min Act: -0.0000

Data Index: 1118544 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 3.6844. Min Range: -3.6844

Max Act: 1.9697. Min Act: -0.0000

Data Index: 1477602 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 3.6844. Min Range: -3.6844

Max Act: 2.0630. Min Act: -0.0000

Data Index: 131092 (The Pile)

Max Activating Token Index: 275