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

Dataset: The Pile

Neuron 182 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.3504. Min Act: -0.0000

Data Index: 153071 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.7847. Min Act: -0.0000

Data Index: 933222 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.6134. Min Act: -0.0000

Data Index: 1973084 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.2211. Min Act: -0.0000

Data Index: 954667 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.8941. Min Act: -0.0000

Data Index: 293118 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.1786. Min Act: -0.0000

Data Index: 369682 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.8829. Min Act: -0.0000

Data Index: 225866 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.2086. Min Act: -0.0000

Data Index: 791474 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.9417. Min Act: -0.0000

Data Index: 240644 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.7910. Min Act: -0.0000

Data Index: 1767558 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.5850. Min Act: -0.0000

Data Index: 1698519 (The Pile)

Max Activating Token Index: 421

Text #11

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.6743. Min Act: -0.0000

Data Index: 14471 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 8.8941. Min Range: -8.8941

Max Act: 6.2842. Min Act: -0.0000

Data Index: 858844 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.5448. Min Act: -0.0000

Data Index: 506351 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.0972. Min Act: -0.0000

Data Index: 831785 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 8.8941. Min Range: -8.8941

Max Act: 6.8799. Min Act: -0.0000

Data Index: 1655665 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 8.8941. Min Range: -8.8941

Max Act: 8.0113. Min Act: -0.0000

Data Index: 501072 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.7607. Min Act: -0.0000

Data Index: 1973 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.5378. Min Act: -0.0000

Data Index: 1869710 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 8.8941. Min Range: -8.8941

Max Act: 7.0772. Min Act: -0.0000

Data Index: 808104 (The Pile)

Max Activating Token Index: 918