Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5937. Min Act: -0.0000

Data Index: 322908 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5830. Min Act: -0.0000

Data Index: 441639 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5291. Min Act: -0.0000

Data Index: 383888 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1252771 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1443220 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: -0.0000

Data Index: 259746 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4801. Min Act: -0.0000

Data Index: 44214 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5272. Min Act: -0.0000

Data Index: 330606 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1911046 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1169136 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1652455 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4791. Min Act: -0.0000

Data Index: 57050 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4920. Min Act: -0.0000

Data Index: 92610 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4742. Min Act: -0.0000

Data Index: 756693 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1070669 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1374886 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1697733 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1011126 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1058296 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4833. Min Act: -0.0000

Data Index: 785689 (The Pile)

Max Activating Token Index: 443