Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 397 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.6843. Min Act: -0.0000

Data Index: 322112 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.6813. Min Act: -0.0000

Data Index: 579486 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1454759 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1822571 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1534613 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1908792 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1889635 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1146424 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5093. Min Act: -0.0000

Data Index: 581755 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1317539 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5121. Min Act: -0.0000

Data Index: 272099 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5245. Min Act: -0.0000

Data Index: 819389 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.5040. Min Act: -0.0000

Data Index: 846545 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1394917 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4696. Min Act: -0.0000

Data Index: 208209 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4557. Min Act: -0.0000

Data Index: 227845 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4833. Min Act: -0.0000

Data Index: 814865 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1050701 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4375. Min Act: -0.0000

Data Index: 16452 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 0.6843. Min Range: -0.6843

Max Act: 0.4664. Min Act: -0.0000

Data Index: 769097 (The Pile)

Max Activating Token Index: 107