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

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

Neuron 4927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1425. Min Range: -4.1425

Max Act: 4.0710. Min Act: -0.0000

Data Index: 395397 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.9329. Min Act: -0.0000

Data Index: 919485 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.9828. Min Act: -0.0000

Data Index: 1163338 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 4.1425. Min Range: -4.1425

Max Act: 4.1425. Min Act: -0.0000

Data Index: 645076 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1065511 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.4351. Min Act: -0.0000

Data Index: 1048526 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.3505. Min Act: -0.0000

Data Index: 210220 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 4.1425. Min Range: -4.1425

Max Act: 3.0909. Min Act: -0.0000

Data Index: 1222592 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.9765. Min Act: -0.0000

Data Index: 1066106 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.6560. Min Act: -0.0000

Data Index: 533456 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.6737. Min Act: -0.0000

Data Index: 1297094 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.5444. Min Act: -0.0000

Data Index: 230180 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.6595. Min Act: -0.0000

Data Index: 494087 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.5710. Min Act: -0.0000

Data Index: 881723 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.3514. Min Act: -0.0000

Data Index: 527887 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.3863. Min Act: -0.0000

Data Index: 629067 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.3474. Min Act: -0.0000

Data Index: 20401 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.4661. Min Act: -0.0000

Data Index: 617137 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.4570. Min Act: -0.0000

Data Index: 2222 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.1425. Min Range: -4.1425

Max Act: 2.1963. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 900