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

Dataset: The Pile

Neuron 3928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0000

Data Index: 773953 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0000

Data Index: 889241 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0040. Min Act: -0.0000

Data Index: 352321 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0033. Min Act: -0.0000

Data Index: 1036299 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0036. Min Act: -0.0000

Data Index: 757023 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0032. Min Act: -0.0000

Data Index: 22955 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0028. Min Act: -0.0000

Data Index: 287365 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0024. Min Act: -0.0000

Data Index: 38307 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0024. Min Act: -0.0000

Data Index: 1817595 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1815971 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0027. Min Act: -0.0000

Data Index: 17981 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0020. Min Act: -0.0000

Data Index: 488134 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0023. Min Act: -0.0000

Data Index: 1505042 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0023. Min Act: -0.0000

Data Index: 756390 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0021. Min Act: -0.0000

Data Index: 1892426 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0021. Min Act: -0.0000

Data Index: 465520 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0020. Min Act: -0.0000

Data Index: 19930 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1055457 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0020. Min Act: -0.0000

Data Index: 173718 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0022. Min Act: -0.0000

Data Index: 696348 (The Pile)

Max Activating Token Index: 871