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

Dataset: The Pile

Neuron 1168 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: 0.0949. Min Range: -0.0949

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1777040 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0945. Min Act: -0.0000

Data Index: 617252 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0922. Min Act: -0.0000

Data Index: 493099 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0891. Min Act: -0.0000

Data Index: 190556 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0878. Min Act: 0.0000

Data Index: 548266 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0871. Min Act: -0.0000

Data Index: 573672 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0868. Min Act: -0.0000

Data Index: 510130 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1575966 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1620911 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1662838 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0811. Min Act: -0.0000

Data Index: 556352 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1508180 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0806. Min Act: -0.0000

Data Index: 515684 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0801. Min Act: -0.0000

Data Index: 656 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0799. Min Act: -0.0000

Data Index: 729993 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0799. Min Act: 0.0000

Data Index: 1724502 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1488394 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0793. Min Act: -0.0000

Data Index: 166819 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0792. Min Act: -0.0000

Data Index: 482830 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.0949. Min Range: -0.0949

Max Act: 0.0792. Min Act: -0.0000

Data Index: 145264 (The Pile)

Max Activating Token Index: 1023