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

Dataset: The Pile

Neuron 1734 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: 3.0568. Min Range: -3.0568

Max Act: 3.0568. Min Act: -0.0000

Data Index: 156593 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 3.0568. Min Range: -3.0568

Max Act: 3.0471. Min Act: -0.0000

Data Index: 130191 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 3.0568. Min Range: -3.0568

Max Act: 3.0216. Min Act: -0.0000

Data Index: 1952208 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.7219. Min Act: -0.0000

Data Index: 1829533 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.8487. Min Act: -0.0000

Data Index: 570673 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.9022. Min Act: -0.0000

Data Index: 1604409 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.7259. Min Act: -0.0000

Data Index: 1663502 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.5433. Min Act: -0.0000

Data Index: 501393 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4838. Min Act: -0.0000

Data Index: 651579 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.5986. Min Act: -0.0000

Data Index: 175025 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1547452 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.6794. Min Act: -0.0000

Data Index: 155034 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.6362. Min Act: -0.0000

Data Index: 218676 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.3891. Min Act: -0.0000

Data Index: 885710 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4895. Min Act: -0.0000

Data Index: 279347 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4669. Min Act: -0.0000

Data Index: 1588849 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.5550. Min Act: -0.0000

Data Index: 39362 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.6630. Min Act: -0.0000

Data Index: 1916220 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4178. Min Act: -0.0000

Data Index: 395718 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 3.0568. Min Range: -3.0568

Max Act: 2.4553. Min Act: -0.0000

Data Index: 444247 (The Pile)

Max Activating Token Index: 444