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

Dataset: The Pile

Neuron 2242 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: 1.4797. Min Range: -1.4797

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1305939 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1676928 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1403501 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1699355 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.3904. Min Act: -0.0000

Data Index: 654613 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1734213 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1259208 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1999392 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2673. Min Act: -0.0000

Data Index: 1024834 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1941. Min Act: -0.0000

Data Index: 165035 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1992033 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1703986 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0083. Min Act: -0.0000

Data Index: 291655 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2379. Min Act: -0.0000

Data Index: 603790 (The Pile)

Max Activating Token Index: 76

Text #14

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1747035 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1994962 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1300791 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1051. Min Act: -0.0000

Data Index: 173752 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0430. Min Act: -0.0000

Data Index: 817146 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0991. Min Act: -0.0000

Data Index: 537388 (The Pile)

Max Activating Token Index: 858