Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1186 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1546487 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1647699 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0908. Min Act: 0.0000

Data Index: 1547863 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1648359 (Python Code)

Max Activating Token Index: 1013

Text #4

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0840. Min Act: 0.0003

Data Index: 1533657 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1614571 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0865. Min Act: 0.0000

Data Index: 1590639 (Python Code)

Max Activating Token Index: 476

Text #7

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1489695 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1559013 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1564650 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1438282 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0840. Min Act: 0.0003

Data Index: 1375307 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1405864 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0814. Min Act: 0.0000

Data Index: 1571393 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1566105 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1632196 (Python Code)

Max Activating Token Index: 735

Text #16

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1647869 (Python Code)

Max Activating Token Index: 898

Text #17

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1590631 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1424344 (Python Code)

Max Activating Token Index: 168

Text #19

Max Range: 0.1033. Min Range: -0.1033

Max Act: 0.0792. Min Act: 0.0001

Data Index: 1413023 (Python Code)

Max Activating Token Index: 895