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

Dataset: The Pile

Neuron 675 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1986193 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0875. Min Act: -0.0000

Data Index: 443797 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1778563 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0732. Min Act: -0.0000

Data Index: 812694 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0715. Min Act: -0.0000

Data Index: 790170 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1337351 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1840774 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0676. Min Act: -0.0000

Data Index: 537708 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0676. Min Act: -0.0000

Data Index: 158133 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1081891 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1610751 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1362223 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1629875 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1552924 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0640. Min Act: -0.0000

Data Index: 166288 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1735324 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0637. Min Act: -0.0000

Data Index: 465538 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0635. Min Act: -0.0000

Data Index: 791126 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0632. Min Act: -0.0000

Data Index: 73279 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0628. Min Act: -0.0000

Data Index: 891591 (The Pile)

Max Activating Token Index: 10