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

Dataset: The Pile

Neuron 4777 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: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1149922 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1794726 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1040944 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1781188 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1661380 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1887645 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1315782 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1536259 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1706637 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1022. Min Act: -0.0000

Data Index: 811813 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0935. Min Act: -0.0000

Data Index: 107460 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1162847 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0925. Min Act: -0.0000

Data Index: 107443 (The Pile)

Max Activating Token Index: 73

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0929. Min Act: -0.0000

Data Index: 11339 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1405986 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1426523 (The Pile)

Max Activating Token Index: 826

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1740825 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0894. Min Act: -0.0000

Data Index: 966506 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0892. Min Act: -0.0000

Data Index: 969630 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1510746 (The Pile)

Max Activating Token Index: 737