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

Dataset: The Pile

Neuron 61 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: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1339883 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1243602 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 323169 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0000

Data Index: 1837553 (The Pile)

Max Activating Token Index: 11

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1694665 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1120520 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 364467 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 142378 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 233047 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 117666 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 480579 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1689134 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1613729 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 331 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1202068 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1346427 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1986589 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 986316 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 863530 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 1303455 (The Pile)

Max Activating Token Index: 956