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

Dataset: The Pile

Neuron 2024 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: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: 0.0000

Data Index: 1019406 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0974. Min Act: -0.0000

Data Index: 329249 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0985. Min Act: 0.0000

Data Index: 1271131 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0950. Min Act: 0.0000

Data Index: 1040493 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0934. Min Act: 0.0000

Data Index: 324905 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0902. Min Act: -0.0000

Data Index: 143617 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0889. Min Act: 0.0001

Data Index: 1552494 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0831. Min Act: 0.0000

Data Index: 1922032 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0857. Min Act: 0.0000

Data Index: 573959 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0848. Min Act: 0.0000

Data Index: 600281 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0817. Min Act: 0.0000

Data Index: 1232728 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0814. Min Act: 0.0000

Data Index: 1125410 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0811. Min Act: 0.0000

Data Index: 287366 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0777. Min Act: 0.0000

Data Index: 803378 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1682077 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0774. Min Act: 0.0001

Data Index: 890453 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0773. Min Act: 0.0000

Data Index: 1893325 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0761. Min Act: 0.0000

Data Index: 187652 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0752. Min Act: -0.0000

Data Index: 691979 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0751. Min Act: 0.0001

Data Index: 480724 (The Pile)

Max Activating Token Index: 204