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

Dataset: The Pile

Neuron 4217 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: 7.8857. Min Range: -7.8857

Max Act: 7.6240. Min Act: -0.0000

Data Index: 823425 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.8857. Min Act: -0.0000

Data Index: 362185 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3160. Min Act: -0.0000

Data Index: 874952 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.8665. Min Act: -0.0000

Data Index: 1435475 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3233. Min Act: -0.0000

Data Index: 1853502 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.4852. Min Act: -0.0000

Data Index: 414472 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.4552. Min Act: -0.0000

Data Index: 288109 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.5696. Min Act: -0.0000

Data Index: 1236151 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3717. Min Act: -0.0000

Data Index: 1863013 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.9116. Min Act: -0.0000

Data Index: 1077941 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.0613. Min Act: -0.0000

Data Index: 12802 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3274. Min Act: -0.0000

Data Index: 1220136 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3640. Min Act: -0.0000

Data Index: 677376 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.0018. Min Act: -0.0000

Data Index: 528343 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 7.8857. Min Range: -7.8857

Max Act: 7.3145. Min Act: -0.0000

Data Index: 1656770 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.8179. Min Act: -0.0000

Data Index: 1516307 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.9326. Min Act: -0.0000

Data Index: 92787 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.7647. Min Act: -0.0000

Data Index: 1993166 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.3609. Min Act: -0.0000

Data Index: 715780 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 7.8857. Min Range: -7.8857

Max Act: 6.9040. Min Act: -0.0000

Data Index: 1436095 (The Pile)

Max Activating Token Index: 690