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

Dataset: The Pile

Neuron 2708 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: 1.4274. Min Range: -1.4274

Max Act: 1.4274. Min Act: -0.0000

Data Index: 446050 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 1.4274. Min Range: -1.4274

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1416370 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.4274. Min Range: -1.4274

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1157395 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.4274. Min Range: -1.4274

Max Act: 1.0529. Min Act: -0.0000

Data Index: 550667 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.9813. Min Act: -0.0000

Data Index: 61029 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.9111. Min Act: -0.0000

Data Index: 155913 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.9022. Min Act: -0.0000

Data Index: 68365 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1526858 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1460768 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8799. Min Act: -0.0000

Data Index: 822763 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8796. Min Act: -0.0000

Data Index: 977618 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8759. Min Act: -0.0000

Data Index: 385546 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8709. Min Act: -0.0000

Data Index: 533600 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8349. Min Act: -0.0000

Data Index: 498860 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1024810 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8751. Min Act: -0.0000

Data Index: 695668 (The Pile)

Max Activating Token Index: 19

Text #16

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1840693 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1851337 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8381. Min Act: -0.0000

Data Index: 843568 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.4274. Min Range: -1.4274

Max Act: 0.8083. Min Act: -0.0000

Data Index: 536470 (The Pile)

Max Activating Token Index: 856