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

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

Neuron 2808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1251. Min Range: -2.1251

Max Act: 2.1251. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.1251. Min Range: -2.1251

Max Act: 2.0987. Min Act: -0.0000

Data Index: 575619 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5314. Min Act: -0.0000

Data Index: 158880 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5995. Min Act: -0.0000

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.4032. Min Act: -0.0000

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3085. Min Act: -0.0000

Data Index: 816387 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2860. Min Act: -0.0000

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3686. Min Act: -0.0000

Data Index: 360784 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3624. Min Act: -0.0000

Data Index: 1296119 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1021559 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3788. Min Act: -0.0000

Data Index: 200269 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2107. Min Act: -0.0000

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1350578 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2774. Min Act: -0.0000

Data Index: 949268 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2807. Min Act: 0.0000

Data Index: 1333884 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1196752 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.1977. Min Act: -0.0000

Data Index: 901506 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.1892. Min Act: -0.0000

Data Index: 548523 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.1908. Min Act: -0.0000

Data Index: 923724 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.2579. Min Act: -0.0000

Data Index: 354171 (C4 (Web Text))

Max Activating Token Index: 228