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

Dataset: The Pile

Neuron 3949 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.1038. Min Act: -0.0000

Data Index: 779008 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1105518 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0753. Min Act: -0.0000

Data Index: 275404 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9978. Min Act: -0.0000

Data Index: 324604 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0329. Min Act: -0.0000

Data Index: 126464 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0727. Min Act: -0.0000

Data Index: 125114 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1142070 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0393. Min Act: -0.0000

Data Index: 183128 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0393. Min Act: -0.0000

Data Index: 128133 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1520255 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1195615 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1598497 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9780. Min Act: -0.0000

Data Index: 721568 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1773885 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9609. Min Act: -0.0000

Data Index: 854096 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1134031 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1533121 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.1038. Min Range: -1.1038

Max Act: 1.0140. Min Act: -0.0000

Data Index: 185846 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9961. Min Act: -0.0000

Data Index: 441157 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 1.1038. Min Range: -1.1038

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1355602 (The Pile)

Max Activating Token Index: 11