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

Dataset: The Pile

Neuron 2007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1702271 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7607. Min Act: -0.0000

Data Index: 218612 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7870. Min Act: -0.0000

Data Index: 16009 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1392402 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1166253 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1685090 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.7270. Min Act: -0.0000

Data Index: 271452 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1054209 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1308969 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5979. Min Act: -0.0000

Data Index: 625182 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6554. Min Act: -0.0000

Data Index: 62576 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6687. Min Act: -0.0000

Data Index: 804146 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6705. Min Act: -0.0000

Data Index: 506722 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6541. Min Act: -0.0000

Data Index: 668692 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6071. Min Act: -0.0000

Data Index: 859672 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6219. Min Act: -0.0000

Data Index: 53437 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1765632 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6227. Min Act: -0.0000

Data Index: 747368 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1195946 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.7870. Min Range: -0.7870

Max Act: 0.6605. Min Act: -0.0000

Data Index: 400972 (The Pile)

Max Activating Token Index: 615