Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: 0.0000

Data Index: 1106197 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2081. Min Act: -0.0000

Data Index: 362164 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2266. Min Act: -0.0000

Data Index: 730566 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1645214 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1987. Min Act: -0.0000

Data Index: 481535 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2189. Min Act: -0.0000

Data Index: 496956 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1841. Min Act: -0.0000

Data Index: 202446 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2024. Min Act: -0.0000

Data Index: 586372 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1711884 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1956869 (The Pile)

Max Activating Token Index: 218

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2022. Min Act: -0.0000

Data Index: 167124 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1263963 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1990. Min Act: -0.0000

Data Index: 427212 (The Pile)

Max Activating Token Index: 892

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2034. Min Act: -0.0000

Data Index: 363301 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1330742 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1215490 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1952. Min Act: -0.0000

Data Index: 603226 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1891. Min Act: 0.0000

Data Index: 158564 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1215308 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1721705 (The Pile)

Max Activating Token Index: 556