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

Dataset: The Pile

Neuron 744 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2310. Min Act: -0.0000

Data Index: 756244 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2178. Min Act: -0.0000

Data Index: 987340 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1190168 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1810221 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2104. Min Act: -0.0000

Data Index: 521328 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1949. Min Act: -0.0000

Data Index: 231571 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2036. Min Act: -0.0000

Data Index: 380011 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2043. Min Act: -0.0000

Data Index: 13830 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1414258 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1927. Min Act: -0.0000

Data Index: 426096 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2000. Min Act: -0.0000

Data Index: 669176 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1919598 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1790. Min Act: -0.0000

Data Index: 990135 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1842. Min Act: -0.0000

Data Index: 773955 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1574071 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1745. Min Act: -0.0000

Data Index: 991841 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1938839 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1678. Min Act: -0.0000

Data Index: 942819 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1582474 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1459329 (The Pile)

Max Activating Token Index: 881