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

Dataset: The Pile

Neuron 4539 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: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: 0.0004

Data Index: 211124 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0963. Min Act: 0.0006

Data Index: 365622 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0998. Min Act: 0.0006

Data Index: 1810505 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0958. Min Act: 0.0003

Data Index: 382107 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0935. Min Act: 0.0004

Data Index: 1724677 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0931. Min Act: 0.0001

Data Index: 779261 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0920. Min Act: 0.0005

Data Index: 846771 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0919. Min Act: 0.0002

Data Index: 723688 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0911. Min Act: 0.0004

Data Index: 461079 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0943. Min Act: 0.0001

Data Index: 1544722 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0906. Min Act: 0.0006

Data Index: 1543586 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0906. Min Act: 0.0005

Data Index: 517542 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0891. Min Act: 0.0005

Data Index: 1616508 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0885. Min Act: 0.0006

Data Index: 423578 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0876. Min Act: 0.0002

Data Index: 1999333 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0866. Min Act: 0.0003

Data Index: 206362 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0867. Min Act: 0.0004

Data Index: 980426 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0847. Min Act: 0.0000

Data Index: 1303892 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0878. Min Act: 0.0003

Data Index: 1102618 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0847. Min Act: 0.0006

Data Index: 350588 (The Pile)

Max Activating Token Index: 943