Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1607227 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2640. Min Act: -0.0001

Data Index: 471424 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2438. Min Act: -0.0001

Data Index: 59576 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2164. Min Act: -0.0000

Data Index: 875017 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2209. Min Act: -0.0000

Data Index: 8502 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1695103 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1438623 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1201766 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1928. Min Act: -0.0000

Data Index: 641471 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1787622 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1378499 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1238001 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1977. Min Act: -0.0000

Data Index: 551527 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1786508 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1880543 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1344295 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1943946 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1281344 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1952. Min Act: -0.0000

Data Index: 807501 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1933. Min Act: -0.0001

Data Index: 641665 (The Pile)

Max Activating Token Index: 390