Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.4354. Min Act: -0.0001

Data Index: 276194 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.3512. Min Act: -0.0001

Data Index: 965846 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.2999. Min Act: -0.0001

Data Index: 599899 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.2631. Min Act: -0.0001

Data Index: 1251406 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.1759. Min Act: -0.0001

Data Index: 1145423 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.2265. Min Act: -0.0001

Data Index: 355895 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.1429. Min Act: -0.0001

Data Index: 1111221 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.2012. Min Act: -0.0001

Data Index: 792748 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.1192. Min Act: -0.0001

Data Index: 1132255 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.1662. Min Act: -0.0001

Data Index: 754356 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0399. Min Act: -0.0001

Data Index: 752336 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0918. Min Act: -0.0001

Data Index: 597957 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.1315. Min Act: -0.0001

Data Index: 721601 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0906. Min Act: -0.0001

Data Index: 685950 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0855. Min Act: -0.0001

Data Index: 787124 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0773. Min Act: -0.0001

Data Index: 960442 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0793. Min Act: -0.0001

Data Index: 1191557 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0689. Min Act: -0.0001

Data Index: 1175432 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.4354. Min Range: -1.4354

Max Act: 0.9523. Min Act: -0.0001

Data Index: 545500 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.4354. Min Range: -1.4354

Max Act: 1.0015. Min Act: -0.0001

Data Index: 471642 (C4 (Web Text))

Max Activating Token Index: 476