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

Dataset: The Pile

Neuron 1429 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: 0.9719. Min Range: -0.9719

Max Act: 0.9719. Min Act: -0.0000

Data Index: 956164 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6251. Min Act: -0.0000

Data Index: 941397 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1927458 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7028. Min Act: -0.0000

Data Index: 944854 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6276. Min Act: -0.0000

Data Index: 662693 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1435677 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1557196 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6397. Min Act: -0.0000

Data Index: 759085 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7221. Min Act: -0.0000

Data Index: 1520040 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6464. Min Act: -0.0000

Data Index: 899967 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1342887 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6110. Min Act: -0.0000

Data Index: 957205 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1202296 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1264586 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1407021 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6041. Min Act: 0.0000

Data Index: 755757 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5673. Min Act: 0.0001

Data Index: 988841 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1961429 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.5660. Min Act: -0.0000

Data Index: 11260 (The Pile)

Max Activating Token Index: 952