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

Dataset: The Pile

Neuron 1592 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: 1.1016. Min Range: -1.1016

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1496590 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.1016. Min Act: -0.0000

Data Index: 352234 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1851565 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1740039 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 1.1016. Min Range: -1.1016

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1802179 (The Pile)

Max Activating Token Index: 475

Text #5

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1244929 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1808058 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1715708 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9493. Min Act: -0.0000

Data Index: 449408 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9391. Min Act: -0.0000

Data Index: 40821 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8812. Min Act: -0.0000

Data Index: 287725 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1768050 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8716. Min Act: -0.0000

Data Index: 880572 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8941. Min Act: -0.0000

Data Index: 795880 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8556. Min Act: -0.0000

Data Index: 19649 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1540969 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1551436 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.7889. Min Act: -0.0000

Data Index: 593231 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8617. Min Act: -0.0000

Data Index: 607924 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 1.1016. Min Range: -1.1016

Max Act: 0.8875. Min Act: -0.0000

Data Index: 903257 (The Pile)

Max Activating Token Index: 303