Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6078. Min Act: -0.0000

Data Index: 353607 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1843903 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5976. Min Act: -0.0000

Data Index: 605891 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6229. Min Act: -0.0000

Data Index: 374070 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5376. Min Act: -0.0000

Data Index: 140577 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1285190 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1612737 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1667220 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6066. Min Act: -0.0000

Data Index: 221328 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1914894 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5411. Min Act: -0.0000

Data Index: 547582 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5438. Min Act: -0.0000

Data Index: 38978 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1409730 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5340. Min Act: -0.0000

Data Index: 680993 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1441323 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5014. Min Act: -0.0000

Data Index: 989100 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1074251 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1201300 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1580187 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1403877 (The Pile)

Max Activating Token Index: 274