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

Dataset: The Pile

Neuron 2402 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: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0000

Data Index: 745164 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1728962 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1492562 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0902. Min Act: -0.0000

Data Index: 154133 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0841. Min Act: -0.0000

Data Index: 328626 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0834. Min Act: -0.0000

Data Index: 943681 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0830. Min Act: -0.0000

Data Index: 807474 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0830. Min Act: -0.0000

Data Index: 155111 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0828. Min Act: -0.0000

Data Index: 819679 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0813. Min Act: -0.0000

Data Index: 80878 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1888441 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1699993 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1670299 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0789. Min Act: -0.0000

Data Index: 464744 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0786. Min Act: -0.0000

Data Index: 267706 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1955771 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1897997 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0746. Min Act: -0.0000

Data Index: 187650 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0772. Min Act: -0.0000

Data Index: 124016 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0763. Min Act: -0.0000

Data Index: 85851 (The Pile)

Max Activating Token Index: 1023