Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 637 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2527. Min Act: -0.0003

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2280. Min Act: -0.0003

Data Index: 442533 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2123. Min Act: -0.0003

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2372. Min Act: -0.0003

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2226. Min Act: -0.0003

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2058. Min Act: -0.0003

Data Index: 381624 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1808. Min Act: -0.0003

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1809. Min Act: -0.0003

Data Index: 550218 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2179. Min Act: -0.0003

Data Index: 563865 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1851. Min Act: -0.0003

Data Index: 972756 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1782. Min Act: -0.0003

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1895. Min Act: -0.0003

Data Index: 339177 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.2010. Min Act: -0.0003

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1817. Min Act: -0.0003

Data Index: 979551 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1732. Min Act: -0.0003

Data Index: 243816 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1761. Min Act: -0.0003

Data Index: 999249 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1767. Min Act: -0.0003

Data Index: 961729 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1631. Min Act: -0.0003

Data Index: 1110086 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1395. Min Act: -0.0003

Data Index: 972437 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.2527. Min Range: -0.2527

Max Act: 0.1567. Min Act: -0.0003

Data Index: 340674 (C4 (Web Text))

Max Activating Token Index: 610