Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 64 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1251940 (The Pile)

Max Activating Token Index: 999

Text #1

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1988855 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1356652 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1645222 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1605917 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1045426 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1769907 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1046711 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3852. Min Act: -0.0000

Data Index: 480581 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3960. Min Act: -0.0000

Data Index: 85318 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3403. Min Act: -0.0000

Data Index: 245000 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3873. Min Act: -0.0000

Data Index: 760060 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3698. Min Act: -0.0000

Data Index: 135291 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1188716 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3825. Min Act: -0.0000

Data Index: 767149 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1276021 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4046. Min Act: -0.0000

Data Index: 110611 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1716661 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1299561 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3831. Min Act: -0.0000

Data Index: 707526 (The Pile)

Max Activating Token Index: 571