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

Dataset: The Pile

Neuron 197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.7156. Min Act: -0.0000

Data Index: 29068 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1750108 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.6914. Min Act: -0.0000

Data Index: 967060 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1913649 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1643970 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3032. Min Act: -0.0000

Data Index: 773624 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1838179 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3694. Min Act: -0.0000

Data Index: 948373 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3156. Min Act: -0.0000

Data Index: 339813 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4365. Min Act: -0.0000

Data Index: 469459 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3599. Min Act: -0.0000

Data Index: 187144 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2771. Min Act: -0.0000

Data Index: 835913 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4165. Min Act: -0.0000

Data Index: 737478 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2646. Min Act: -0.0000

Data Index: 1636153 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1388088 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1941184 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3141. Min Act: -0.0000

Data Index: 369635 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1609241 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1796849 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1780763 (The Pile)

Max Activating Token Index: 874