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

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

Neuron 5870 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: 0.2616. Min Range: -0.2616

Max Act: 0.2616. Min Act: -0.0000

Data Index: 810628 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2006. Min Act: -0.0000

Data Index: 257699 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1561947 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1909. Min Act: -0.0000

Data Index: 477079 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1892. Min Act: -0.0000

Data Index: 290977 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1447843 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1882. Min Act: -0.0000

Data Index: 507110 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1982. Min Act: -0.0000

Data Index: 756819 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1606298 (Python Code)

Max Activating Token Index: 800

Text #9

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1426079 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1842. Min Act: -0.0000

Data Index: 839446 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1855. Min Act: -0.0000

Data Index: 551236 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1704. Min Act: -0.0000

Data Index: 78283 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1498807 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1401304 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1656. Min Act: -0.0000

Data Index: 147039 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1700. Min Act: -0.0000

Data Index: 211347 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1521. Min Act: -0.0000

Data Index: 342717 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1620427 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1440998 (Python Code)

Max Activating Token Index: 347