Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2318. Min Act: -0.0002

Data Index: 887102 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2152. Min Act: -0.0002

Data Index: 40802 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2323. Min Act: -0.0002

Data Index: 266785 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1900. Min Act: -0.0002

Data Index: 1250750 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2047. Min Act: -0.0002

Data Index: 244692 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1865. Min Act: -0.0002

Data Index: 510688 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2180. Min Act: -0.0002

Data Index: 1134960 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1969. Min Act: -0.0002

Data Index: 907203 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.2036. Min Act: -0.0002

Data Index: 1347601 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1815. Min Act: -0.0002

Data Index: 342507 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1034785 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1884. Min Act: -0.0002

Data Index: 24239 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1803. Min Act: -0.0002

Data Index: 854683 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1106073 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1784. Min Act: -0.0002

Data Index: 1097744 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1880. Min Act: -0.0002

Data Index: 1145497 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1785. Min Act: -0.0002

Data Index: 437464 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1765. Min Act: -0.0002

Data Index: 1313481 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1730. Min Act: -0.0002

Data Index: 477012 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.2323. Min Range: -0.2323

Max Act: 0.1833. Min Act: -0.0002

Data Index: 769723 (C4 (Web Text))

Max Activating Token Index: 597