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

Dataset: The Pile

Neuron 34 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1521067 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4317. Min Act: -0.0000

Data Index: 894086 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4043. Min Act: -0.0000

Data Index: 18035 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1102362 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4508. Min Act: -0.0000

Data Index: 211896 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3758. Min Act: -0.0000

Data Index: 777978 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1116736 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1091707 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1596425 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3265. Min Act: -0.0000

Data Index: 433300 (The Pile)

Max Activating Token Index: 161

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1200255 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3369. Min Act: -0.0000

Data Index: 377219 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3168. Min Act: -0.0000

Data Index: 286325 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1131144 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3050. Min Act: -0.0000

Data Index: 461818 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1857424 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1667703 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3117. Min Act: -0.0000

Data Index: 703408 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3201. Min Act: -0.0000

Data Index: 629317 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1373984 (The Pile)

Max Activating Token Index: 78