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

Dataset: The Pile

Neuron 4709 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: 0.2854. Min Range: -0.2854

Max Act: 0.2854. Min Act: -0.0000

Data Index: 791927 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1319634 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2266. Min Act: -0.0000

Data Index: 356492 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2168. Min Act: -0.0000

Data Index: 401136 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2142. Min Act: -0.0000

Data Index: 973267 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1755211 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1277663 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1030019 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1968. Min Act: -0.0000

Data Index: 689598 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1548172 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1276418 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1877. Min Act: -0.0000

Data Index: 382740 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1940147 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1887. Min Act: -0.0000

Data Index: 335572 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1864. Min Act: -0.0000

Data Index: 906883 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1802. Min Act: -0.0000

Data Index: 129783 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1377579 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1110646 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1648. Min Act: -0.0000

Data Index: 616458 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.2854. Min Range: -0.2854

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1953161 (The Pile)

Max Activating Token Index: 564