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

Dataset: The Pile

Neuron 2854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1507923 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1783980 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6767. Min Act: -0.0000

Data Index: 577850 (The Pile)

Max Activating Token Index: 31

Text #3

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1226931 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5680. Min Act: -0.0000

Data Index: 499659 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1976759 (The Pile)

Max Activating Token Index: 980

Text #6

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1250899 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5910. Min Act: -0.0000

Data Index: 987724 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1084403 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1704952 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5614. Min Act: -0.0000

Data Index: 695589 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5690. Min Act: -0.0000

Data Index: 829108 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5611. Min Act: -0.0000

Data Index: 154995 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5181. Min Act: -0.0000

Data Index: 293299 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1020560 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5644. Min Act: -0.0000

Data Index: 948402 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5247. Min Act: -0.0000

Data Index: 497016 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5047. Min Act: -0.0000

Data Index: 510278 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1930686 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.7573. Min Range: -0.7573

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1891350 (The Pile)

Max Activating Token Index: 832