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

Dataset: The Pile

Neuron 669 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1215758 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.6808. Min Act: -0.0000

Data Index: 781917 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.8132. Min Act: -0.0000

Data Index: 577532 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1300491 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.6106. Min Act: -0.0000

Data Index: 925705 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1787644 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3041. Min Act: -0.0000

Data Index: 183336 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1787406 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.7040. Min Act: -0.0000

Data Index: 1267349 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5506. Min Act: -0.0000

Data Index: 684216 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.6259. Min Act: -0.0000

Data Index: 536798 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5073. Min Act: -0.0000

Data Index: 881444 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5618. Min Act: -0.0000

Data Index: 343617 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5103. Min Act: -0.0000

Data Index: 523456 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5441. Min Act: -0.0000

Data Index: 595735 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1735187 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1736443 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1688934 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5756. Min Act: -0.0000

Data Index: 432754 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.8139. Min Range: -1.8139

Max Act: 1.5019. Min Act: -0.0000

Data Index: 610635 (The Pile)

Max Activating Token Index: 808