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

Dataset: The Pile

Neuron 1861 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: 1.8836. Min Range: -1.8836

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1854712 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.8499. Min Act: -0.0000

Data Index: 795538 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.8147. Min Act: -0.0000

Data Index: 607165 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7461. Min Act: -0.0000

Data Index: 737860 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7628. Min Act: -0.0000

Data Index: 212177 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1703501 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7122. Min Act: -0.0000

Data Index: 764097 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6905. Min Act: -0.0000

Data Index: 780685 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6782. Min Act: -0.0000

Data Index: 780764 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6818. Min Act: -0.0000

Data Index: 85351 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6103. Min Act: -0.0000

Data Index: 506399 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7108. Min Act: -0.0000

Data Index: 396349 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7063. Min Act: -0.0000

Data Index: 47984 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7056. Min Act: -0.0000

Data Index: 296669 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.5709. Min Act: -0.0000

Data Index: 453932 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.5622. Min Act: -0.0000

Data Index: 281094 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4692. Min Act: -0.0000

Data Index: 360906 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4715. Min Act: -0.0000

Data Index: 296768 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4671. Min Act: -0.0000

Data Index: 636102 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6205. Min Act: -0.0000

Data Index: 124762 (The Pile)

Max Activating Token Index: 962