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

Dataset: The Pile

Neuron 4539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7960. Min Act: -0.0000

Data Index: 985621 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1782429 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1237004 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6173. Min Act: -0.0000

Data Index: 79982 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1828327 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1723430 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1339890 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4891. Min Act: -0.0000

Data Index: 994695 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5070. Min Act: -0.0000

Data Index: 939655 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5096. Min Act: -0.0000

Data Index: 128433 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5472. Min Act: -0.0000

Data Index: 665497 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4471. Min Act: -0.0000

Data Index: 451998 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4401. Min Act: -0.0000

Data Index: 79276 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4564. Min Act: -0.0000

Data Index: 951092 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4926. Min Act: -0.0000

Data Index: 192454 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1655577 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4640. Min Act: -0.0000

Data Index: 275456 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1701958 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4663. Min Act: -0.0000

Data Index: 276845 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.3854. Min Act: -0.0000

Data Index: 151561 (The Pile)

Max Activating Token Index: 975