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

Dataset: The Pile

Neuron 3574 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: 0.2941. Min Range: -0.2941

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1986366 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2741. Min Act: -0.0000

Data Index: 238461 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2617. Min Act: -0.0000

Data Index: 450006 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2088. Min Act: -0.0000

Data Index: 611890 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2102. Min Act: -0.0000

Data Index: 72237 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2121. Min Act: -0.0000

Data Index: 697880 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2262. Min Act: -0.0000

Data Index: 139802 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2018. Min Act: -0.0000

Data Index: 286937 (The Pile)

Max Activating Token Index: 585

Text #8

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1627895 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2043. Min Act: -0.0000

Data Index: 663043 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1131469 (The Pile)

Max Activating Token Index: 679

Text #11

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2066. Min Act: -0.0000

Data Index: 308866 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1401137 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.1990. Min Act: -0.0000

Data Index: 977609 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2030. Min Act: -0.0000

Data Index: 941207 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1015650 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.2070. Min Act: -0.0000

Data Index: 549305 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.1829. Min Act: -0.0000

Data Index: 48255 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1147851 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 0.2941. Min Range: -0.2941

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1550398 (The Pile)

Max Activating Token Index: 554