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

Dataset: The Pile

Neuron 3450 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: 1.7744. Min Range: -1.7744

Max Act: 1.7744. Min Act: -0.0000

Data Index: 1667559 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6514. Min Act: -0.0000

Data Index: 1628497 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.7028. Min Act: -0.0000

Data Index: 941547 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.7050. Min Act: -0.0000

Data Index: 1361294 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6566. Min Act: -0.0000

Data Index: 1502411 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5462. Min Act: -0.0000

Data Index: 115464 (The Pile)

Max Activating Token Index: 944

Text #6

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1490513 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1853722 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5919. Min Act: -0.0000

Data Index: 1145865 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1269850 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6594. Min Act: -0.0000

Data Index: 448527 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1727567 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5976. Min Act: -0.0000

Data Index: 135655 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1813667 (The Pile)

Max Activating Token Index: 29

Text #14

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6325. Min Act: -0.0000

Data Index: 933170 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.4533. Min Act: -0.0000

Data Index: 998145 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1408538 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1152812 (The Pile)

Max Activating Token Index: 931

Text #18

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.6148. Min Act: -0.0000

Data Index: 108404 (The Pile)

Max Activating Token Index: 423

Text #19

Max Range: 1.7744. Min Range: -1.7744

Max Act: 1.5607. Min Act: -0.0000

Data Index: 918967 (The Pile)

Max Activating Token Index: 63