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

Dataset: The Pile

Neuron 732 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: 0.8067. Min Range: -0.8067

Max Act: 0.8067. Min Act: -0.0000

Data Index: 619074 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7025. Min Act: -0.0000

Data Index: 160602 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.7085. Min Act: -0.0000

Data Index: 537218 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5861. Min Act: -0.0000

Data Index: 754137 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5694. Min Act: -0.0000

Data Index: 534037 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1147719 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5218. Min Act: -0.0000

Data Index: 427268 (The Pile)

Max Activating Token Index: 655

Text #7

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1836884 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1055303 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4852. Min Act: -0.0000

Data Index: 536273 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4996. Min Act: -0.0000

Data Index: 908470 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5642. Min Act: -0.0000

Data Index: 668945 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5081. Min Act: -0.0000

Data Index: 508848 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5046. Min Act: -0.0000

Data Index: 424758 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1933685 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1065376 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.5002. Min Act: -0.0000

Data Index: 904904 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1662021 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1032219 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.8067. Min Range: -0.8067

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1780389 (The Pile)

Max Activating Token Index: 37