Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 11 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7693. Min Act: -0.0000

Data Index: 1238841 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1084086 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.7072. Min Act: -0.0000

Data Index: 272184 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1862391 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.6318. Min Act: -0.0000

Data Index: 352460 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.5442. Min Act: -0.0000

Data Index: 70091 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4824. Min Act: -0.0000

Data Index: 544010 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1532299 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.3163. Min Act: -0.0000

Data Index: 1345789 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1944346 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.3897. Min Act: -0.0000

Data Index: 286714 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.1530. Min Act: -0.0000

Data Index: 200422 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1130590 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2367. Min Act: -0.0000

Data Index: 16786 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2362. Min Act: -0.0000

Data Index: 885245 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1138307 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1885812 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1887514 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.2835. Min Act: -0.0000

Data Index: 415967 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 1.8836. Min Range: -1.8836

Max Act: 1.1012. Min Act: -0.0000

Data Index: 427917 (The Pile)

Max Activating Token Index: 178