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

Dataset: The Pile

Neuron 4201 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4756. Min Act: -0.0000

Data Index: 305370 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4597. Min Act: -0.0000

Data Index: 625159 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1722912 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1167067 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4092. Min Act: -0.0000

Data Index: 904660 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1934420 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.4027. Min Act: -0.0000

Data Index: 447575 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1330510 (The Pile)

Max Activating Token Index: 186

Text #8

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3600. Min Act: -0.0000

Data Index: 528688 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3338. Min Act: -0.0000

Data Index: 1966720 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3771. Min Act: -0.0000

Data Index: 472625 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.2976. Min Act: -0.0000

Data Index: 876171 (The Pile)

Max Activating Token Index: 346

Text #12

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1885351 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3047. Min Act: -0.0000

Data Index: 862630 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3229. Min Act: -0.0000

Data Index: 590111 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1460441 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1717091 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.1996. Min Act: -0.0000

Data Index: 68157 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1787453 (The Pile)

Max Activating Token Index: 120

Text #19

Max Range: 1.5887. Min Range: -1.5887

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1743729 (The Pile)

Max Activating Token Index: 999