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

Dataset: The Pile

Neuron 2401 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1449041 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2858. Min Act: 0.0000

Data Index: 900722 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2622. Min Act: 0.0000

Data Index: 384287 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2708. Min Act: -0.0000

Data Index: 94613 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2475. Min Act: -0.0000

Data Index: 249322 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1415794 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2193. Min Act: -0.0000

Data Index: 598274 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2109. Min Act: 0.0000

Data Index: 410616 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2175. Min Act: -0.0001

Data Index: 1448337 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1134381 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1587557 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2044. Min Act: -0.0001

Data Index: 743941 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2008. Min Act: -0.0000

Data Index: 136650 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1865407 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2075. Min Act: -0.0000

Data Index: 19285 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1378380 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1806341 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2063. Min Act: 0.0000

Data Index: 1597787 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2062. Min Act: -0.0000

Data Index: 570736 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.3008. Min Range: -0.3008

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1757006 (The Pile)

Max Activating Token Index: 542