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

Dataset: The Pile

Neuron 885 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: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1797485 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1820210 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1924641 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4974. Min Act: -0.0000

Data Index: 196068 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4507. Min Act: -0.0000

Data Index: 78560 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4346. Min Act: -0.0000

Data Index: 33731 (The Pile)

Max Activating Token Index: 264

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1301415 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4139. Min Act: -0.0000

Data Index: 455119 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4473. Min Act: -0.0000

Data Index: 519915 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4031. Min Act: -0.0000

Data Index: 84247 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1749651 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1374542 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1449977 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3960. Min Act: -0.0000

Data Index: 247701 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3819. Min Act: -0.0000

Data Index: 10437 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3771. Min Act: -0.0000

Data Index: 2973 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1701575 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3810. Min Act: -0.0000

Data Index: 691661 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3827. Min Act: -0.0000

Data Index: 861013 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3919. Min Act: -0.0000

Data Index: 690718 (The Pile)

Max Activating Token Index: 75