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

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

Neuron 3258 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2767. Min Range: -2.2767

Max Act: 2.2767. Min Act: -0.0000

Data Index: 1584074 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 2.2767. Min Range: -2.2767

Max Act: 2.1441. Min Act: -0.0000

Data Index: 1458676 (Python Code)

Max Activating Token Index: 541

Text #2

Max Range: 2.2767. Min Range: -2.2767

Max Act: 2.0339. Min Act: -0.0000

Data Index: 1539901 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1573922 (Python Code)

Max Activating Token Index: 704

Text #4

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.9552. Min Act: -0.0000

Data Index: 1611830 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 2.2767. Min Range: -2.2767

Max Act: 2.0578. Min Act: -0.0000

Data Index: 1421620 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.8095. Min Act: -0.0000

Data Index: 1393434 (Python Code)

Max Activating Token Index: 859

Text #7

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1591053 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1428386 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.9159. Min Act: -0.0000

Data Index: 1622682 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.7876. Min Act: -0.0000

Data Index: 1554808 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.5612. Min Act: -0.0000

Data Index: 1604372 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6723. Min Act: -0.0000

Data Index: 1443334 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.7109. Min Act: -0.0000

Data Index: 1449597 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1360946 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1642512 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1622434 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6621. Min Act: -0.0000

Data Index: 1585493 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1649746 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 2.2767. Min Range: -2.2767

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1538855 (Python Code)

Max Activating Token Index: 468