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

Dataset: The Pile

Neuron 3753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7400. Min Act: -0.0000

Data Index: 458342 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1125262 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1191891 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6054. Min Act: -0.0000

Data Index: 840374 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1556095 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6345. Min Act: -0.0000

Data Index: 555963 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5845. Min Act: -0.0000

Data Index: 355968 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5523. Min Act: -0.0000

Data Index: 976196 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5719. Min Act: -0.0000

Data Index: 43693 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4153. Min Act: -0.0000

Data Index: 336739 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1047169 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1747068 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1212941 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1424244 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5396. Min Act: -0.0000

Data Index: 72806 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5328. Min Act: -0.0000

Data Index: 180330 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1668600 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5780. Min Act: -0.0000

Data Index: 999831 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1532075 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5737. Min Act: -0.0000

Data Index: 682121 (The Pile)

Max Activating Token Index: 564