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

Dataset: The Pile

Neuron 1071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0000

Data Index: 312964 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1569289 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1911167 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0804. Min Act: -0.0000

Data Index: 528594 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0746. Min Act: -0.0000

Data Index: 811422 (The Pile)

Max Activating Token Index: 305

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1600659 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0762. Min Act: -0.0000

Data Index: 835407 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0714. Min Act: -0.0000

Data Index: 526041 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0793. Min Act: -0.0000

Data Index: 73206 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1177321 (The Pile)

Max Activating Token Index: 781

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0799. Min Act: -0.0000

Data Index: 910805 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0794. Min Act: -0.0000

Data Index: 976224 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1488407 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0759. Min Act: -0.0000

Data Index: 399528 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0827. Min Act: -0.0000

Data Index: 965638 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0770. Min Act: -0.0000

Data Index: 532521 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0762. Min Act: -0.0000

Data Index: 444413 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1737242 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1226028 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0736. Min Act: -0.0000

Data Index: 272904 (The Pile)

Max Activating Token Index: 56