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

Dataset: The Pile

Neuron 719 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: 0.6429. Min Range: -0.6429

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1907720 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1919960 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5669. Min Act: -0.0000

Data Index: 729381 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1234201 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1742722 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1496272 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1970761 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1959717 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1231412 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1931756 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5530. Min Act: -0.0000

Data Index: 967225 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5326. Min Act: -0.0000

Data Index: 67018 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5084. Min Act: -0.0000

Data Index: 381389 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1712841 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1836201 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5161. Min Act: -0.0000

Data Index: 139502 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1302853 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1624986 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5203. Min Act: -0.0000

Data Index: 731667 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.6429. Min Range: -0.6429

Max Act: 0.5128. Min Act: -0.0000

Data Index: 439270 (The Pile)

Max Activating Token Index: 120