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

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

Neuron 3238 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: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1567024 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1499540 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1608473 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1590515 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1613556 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1381580 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1406804 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1387008 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1484250 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1644754 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1520898 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1551394 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1553660 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1467571 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1519336 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1520783 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1469620 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1631975 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1390196 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1422176 (Python Code)

Max Activating Token Index: 121