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

Dataset: The Pile

Neuron 3925 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: 1.3613. Min Range: -1.3613

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1727438 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.1023. Min Act: -0.0000

Data Index: 744045 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7895. Min Act: -0.0000

Data Index: 817636 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7832. Min Act: -0.0000

Data Index: 946442 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1829781 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7533. Min Act: -0.0000

Data Index: 487503 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6802. Min Act: -0.0000

Data Index: 962071 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6986. Min Act: -0.0000

Data Index: 635800 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6547. Min Act: -0.0000

Data Index: 464073 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7347. Min Act: -0.0000

Data Index: 324311 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1838069 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.7173. Min Act: -0.0000

Data Index: 543526 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1516453 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1292661 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6808. Min Act: -0.0000

Data Index: 708216 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1870598 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.5367. Min Act: -0.0000

Data Index: 911332 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1172383 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.5985. Min Act: -0.0000

Data Index: 708910 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1128630 (The Pile)

Max Activating Token Index: 758