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

Dataset: The Pile

Neuron 4730 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1355133 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1924723 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1266619 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4306. Min Act: -0.0000

Data Index: 640610 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1595039 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4416. Min Act: -0.0000

Data Index: 454895 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4075. Min Act: -0.0000

Data Index: 30257 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1670578 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.4008. Min Act: -0.0000

Data Index: 540425 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1974009 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1547267 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3898. Min Act: -0.0000

Data Index: 136791 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1461679 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3873. Min Act: -0.0000

Data Index: 403490 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3852. Min Act: -0.0000

Data Index: 613365 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1214966 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3910. Min Act: -0.0000

Data Index: 366199 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1952720 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1743769 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.5009. Min Range: -0.5009

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1287972 (The Pile)

Max Activating Token Index: 162