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

Dataset: The Pile

Neuron 3924 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1672435 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0000

Data Index: 871146 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1506175 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4617. Min Act: -0.0000

Data Index: 32243 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4419. Min Act: 0.0000

Data Index: 80224 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1959108 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1681203 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4083. Min Act: -0.0000

Data Index: 758809 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1270311 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1557807 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1763679 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1485551 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4007. Min Act: -0.0000

Data Index: 811026 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4083. Min Act: 0.0000

Data Index: 995796 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3896. Min Act: -0.0000

Data Index: 610273 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1684656 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3846. Min Act: 0.0000

Data Index: 251418 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1310382 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1757195 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3519. Min Act: 0.0000

Data Index: 1953704 (The Pile)

Max Activating Token Index: 984