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

Dataset: The Pile

Neuron 3322 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: 1.5870. Min Range: -1.5870

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1138784 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4597. Min Act: -0.0000

Data Index: 634352 (The Pile)

Max Activating Token Index: 917

Text #2

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.5027. Min Act: -0.0000

Data Index: 488097 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1058437 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.5551. Min Act: -0.0000

Data Index: 968184 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3908. Min Act: -0.0000

Data Index: 36201 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.5479. Min Act: -0.0000

Data Index: 660519 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1974839 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4510. Min Act: -0.0000

Data Index: 779650 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4637. Min Act: -0.0000

Data Index: 44423 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4309. Min Act: -0.0000

Data Index: 598964 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1504931 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.5870. Min Range: -1.5870

Max Act: 0.8068. Min Act: -0.0000

Data Index: 639507 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3949. Min Act: -0.0000

Data Index: 598049 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3005. Min Act: -0.0000

Data Index: 707444 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3862. Min Act: -0.0000

Data Index: 684503 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3554. Min Act: -0.0000

Data Index: 1070865 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3712. Min Act: -0.0000

Data Index: 774023 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1006438 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4339. Min Act: -0.0000

Data Index: 694010 (The Pile)

Max Activating Token Index: 694