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

Dataset: The Pile

Neuron 1410 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: 1.3938. Min Range: -1.3938

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1575355 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1019326 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2201. Min Act: -0.0000

Data Index: 725829 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2696. Min Act: -0.0000

Data Index: 609580 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2306. Min Act: -0.0000

Data Index: 857076 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2879. Min Act: -0.0000

Data Index: 136586 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.1699. Min Act: -0.0000

Data Index: 297962 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2039. Min Act: -0.0000

Data Index: 949053 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1232287 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0619. Min Act: -0.0000

Data Index: 918518 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1587631 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.1026. Min Act: -0.0000

Data Index: 395915 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9812. Min Act: -0.0000

Data Index: 446564 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9995. Min Act: -0.0000

Data Index: 744374 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0237. Min Act: -0.0000

Data Index: 8407 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1857179 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0520. Min Act: -0.0000

Data Index: 704108 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.0601. Min Act: -0.0000

Data Index: 506886 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1803623 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 1.3938. Min Range: -1.3938

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1150555 (The Pile)

Max Activating Token Index: 26