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

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

Neuron 5902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.1097. Min Act: -0.0000

Data Index: 907541 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0992. Min Act: -0.0000

Data Index: 277976 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1479604 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1654076 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1150435 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1278957 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0947. Min Act: -0.0000

Data Index: 744427 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1461699 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0844. Min Act: -0.0000

Data Index: 824245 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1012347 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1526695 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1552184 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1455839 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1074571 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0800. Min Act: -0.0000

Data Index: 291368 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1054153 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1016238 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1378877 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0756. Min Act: -0.0000

Data Index: 150461 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1097. Min Range: -0.1097

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1490843 (Python Code)

Max Activating Token Index: 1023