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

Dataset: The Pile

Neuron 1052 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: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0000

Data Index: 326140 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1993990 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2845. Min Act: -0.0000

Data Index: 472899 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2561. Min Act: -0.0000

Data Index: 13006 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2310. Min Act: -0.0000

Data Index: 483383 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1998542 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1852. Min Act: -0.0000

Data Index: 466813 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2351. Min Act: -0.0001

Data Index: 265716 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1203121 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1830. Min Act: -0.0000

Data Index: 863669 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1791506 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2127. Min Act: -0.0000

Data Index: 750060 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1032205 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1557163 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2173. Min Act: -0.0000

Data Index: 522208 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1958. Min Act: -0.0000

Data Index: 287975 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2083. Min Act: -0.0000

Data Index: 289717 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1939. Min Act: -0.0000

Data Index: 756698 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1916. Min Act: -0.0001

Data Index: 934903 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1310277 (The Pile)

Max Activating Token Index: 560