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

Dataset: The Pile

Neuron 4250 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: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1205749 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7417. Min Act: -0.0000

Data Index: 801374 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7143. Min Act: -0.0000

Data Index: 970296 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6757. Min Act: -0.0000

Data Index: 467081 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1498349 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1093703 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6117. Min Act: -0.0000

Data Index: 963805 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6308. Min Act: -0.0000

Data Index: 428959 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6086. Min Act: -0.0000

Data Index: 948635 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6194. Min Act: -0.0000

Data Index: 81078 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5087. Min Act: -0.0000

Data Index: 208076 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1610047 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1923924 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5955. Min Act: -0.0000

Data Index: 545850 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1910250 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1009200 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1448812 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5947. Min Act: -0.0000

Data Index: 558131 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5772. Min Act: -0.0000

Data Index: 754293 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1313825 (The Pile)

Max Activating Token Index: 111