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

Dataset: The Pile

Neuron 2569 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.3086. Min Act: -0.0000

Data Index: 455454 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1815510 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9773. Min Act: -0.0000

Data Index: 396464 (The Pile)

Max Activating Token Index: 45

Text #3

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1772068 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9035. Min Act: 0.0000

Data Index: 736181 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1689486 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8625. Min Act: -0.0000

Data Index: 988497 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8543. Min Act: -0.0000

Data Index: 637150 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8511. Min Act: -0.0000

Data Index: 256545 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1865799 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1197963 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1729083 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1667226 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1903792 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1261731 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8096. Min Act: -0.0000

Data Index: 446304 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.7891. Min Act: -0.0000

Data Index: 608016 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1266354 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.7974. Min Act: -0.0000

Data Index: 285497 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1305787 (The Pile)

Max Activating Token Index: 534