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

Dataset: The Pile

Neuron 1866 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: 1.7128. Min Range: -1.7128

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1237567 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.7128. Min Act: -0.0000

Data Index: 861334 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.5267. Min Act: -0.0000

Data Index: 563487 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1553416 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1728844 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.4000. Min Act: -0.0000

Data Index: 733886 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1310620 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1172578 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1507820 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1931607 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1491834 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2778. Min Act: -0.0000

Data Index: 472972 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3418. Min Act: -0.0000

Data Index: 44498 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3180. Min Act: -0.0000

Data Index: 476802 (The Pile)

Max Activating Token Index: 848

Text #14

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1789. Min Act: -0.0000

Data Index: 68159 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1007. Min Act: -0.0000

Data Index: 922131 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1418479 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1597. Min Act: -0.0000

Data Index: 578188 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2264. Min Act: -0.0000

Data Index: 97331 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1975. Min Act: -0.0000

Data Index: 435005 (The Pile)

Max Activating Token Index: 61