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

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

Neuron 3122 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2351. Min Act: -0.0000

Data Index: 855587 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1132952 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2175. Min Act: -0.0000

Data Index: 727986 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1262372 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2035. Min Act: -0.0000

Data Index: 896578 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2097. Min Act: -0.0000

Data Index: 646278 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2053. Min Act: -0.0000

Data Index: 117562 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1045154 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1818. Min Act: -0.0000

Data Index: 95319 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1886. Min Act: -0.0000

Data Index: 295731 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2005. Min Act: -0.0000

Data Index: 837767 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2054. Min Act: -0.0000

Data Index: 85517 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1019446 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1776. Min Act: -0.0000

Data Index: 330815 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1797. Min Act: -0.0000

Data Index: 82556 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1810. Min Act: -0.0000

Data Index: 424922 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1734. Min Act: -0.0000

Data Index: 387400 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1650. Min Act: -0.0000

Data Index: 891493 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1836. Min Act: -0.0000

Data Index: 722337 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1612. Min Act: -0.0000

Data Index: 571038 (C4 (Web Text))

Max Activating Token Index: 136