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

Dataset: The Pile

Neuron 795 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0000

Data Index: 1769528 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 12698 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 18986 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1721 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 20323 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 1226 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 8699 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0001

Data Index: 16755 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 3377 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 14224 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 21654 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0001

Data Index: 18766 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 2323 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 20957 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 24505 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 11058 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 9200 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 4539 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 14017 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0218. Min Act: -0.0000

Data Index: 7083 (The Pile)

Max Activating Token Index: 1