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

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

Neuron 4386 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1390730 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1597422 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1572855 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1652699 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1546572 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1492806 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1390825 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1471037 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1586626 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1417877 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1372574 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1480701 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1410379 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1514408 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1397633 (Python Code)

Max Activating Token Index: 970

Text #15

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1472223 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1477389 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1589597 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1570476 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1363910 (Python Code)

Max Activating Token Index: 6