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

Dataset: The Pile

Neuron 839 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1050929 (The Pile)

Max Activating Token Index: 707

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1268746 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1225087 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5548. Min Act: -0.0000

Data Index: 249350 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1486100 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4966. Min Act: -0.0000

Data Index: 467595 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4985. Min Act: -0.0000

Data Index: 259466 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1005906 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1114613 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1345655 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1464663 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1719627 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1106888 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1123619 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1580864 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4584. Min Act: -0.0000

Data Index: 286972 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4487. Min Act: -0.0000

Data Index: 932536 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1686700 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1803836 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1684800 (The Pile)

Max Activating Token Index: 128