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

Dataset: The Pile

Neuron 1917 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: 1.1914. Min Range: -1.1914

Max Act: 1.1914. Min Act: -0.0000

Data Index: 688171 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1753763 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9041. Min Act: -0.0000

Data Index: 677090 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9257. Min Act: -0.0000

Data Index: 265941 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9082. Min Act: -0.0000

Data Index: 676447 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1747669 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9150. Min Act: -0.0000

Data Index: 661571 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9137. Min Act: -0.0000

Data Index: 240288 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9488. Min Act: -0.0000

Data Index: 370701 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1914626 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1198269 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8540. Min Act: -0.0000

Data Index: 529688 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1056863 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1672442 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9190. Min Act: -0.0000

Data Index: 376337 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8219. Min Act: -0.0000

Data Index: 442884 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1729275 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8677. Min Act: -0.0000

Data Index: 756978 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1007125 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8529. Min Act: -0.0000

Data Index: 877566 (The Pile)

Max Activating Token Index: 246