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

Dataset: The Pile

Neuron 4233 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: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1075489 (The Pile)

Max Activating Token Index: 198

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1633. Min Act: -0.0000

Data Index: 689099 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2269. Min Act: -0.0000

Data Index: 797807 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1401. Min Act: -0.0000

Data Index: 301554 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0277. Min Act: -0.0000

Data Index: 441135 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0989. Min Act: -0.0000

Data Index: 416417 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1402048 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1786413 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1078. Min Act: -0.0000

Data Index: 721813 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0102. Min Act: -0.0000

Data Index: 199581 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0676. Min Act: -0.0000

Data Index: 1557104 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1968503 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1058897 (The Pile)

Max Activating Token Index: 933

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0756. Min Act: -0.0000

Data Index: 824587 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0083. Min Act: -0.0000

Data Index: 771795 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1803031 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1245537 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1858134 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9684. Min Act: -0.0000

Data Index: 762973 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0149. Min Act: -0.0000

Data Index: 629264 (The Pile)

Max Activating Token Index: 66