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

Dataset: The Pile

Neuron 2777 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: 0.2136. Min Range: -0.2136

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1496499 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1940. Min Act: -0.0000

Data Index: 617487 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2099. Min Act: -0.0000

Data Index: 902581 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1653795 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1426220 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1091402 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2123. Min Act: -0.0000

Data Index: 418558 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1214516 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1655. Min Act: -0.0000

Data Index: 175890 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1790. Min Act: -0.0000

Data Index: 526354 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1590906 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1784. Min Act: -0.0000

Data Index: 605859 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1057993 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1800. Min Act: -0.0000

Data Index: 346024 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1762. Min Act: -0.0000

Data Index: 28502 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1832. Min Act: -0.0000

Data Index: 128653 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1948913 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1087326 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1197265 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1923. Min Act: -0.0000

Data Index: 598083 (The Pile)

Max Activating Token Index: 1016