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

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

Neuron 1077 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: 0.2138. Min Range: -0.2138

Max Act: 0.2138. Min Act: -0.0002

Data Index: 537930 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2061. Min Act: -0.0002

Data Index: 131894 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1979. Min Act: -0.0002

Data Index: 659049 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2050. Min Act: -0.0002

Data Index: 222625 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1936. Min Act: -0.0002

Data Index: 1285781 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1933. Min Act: -0.0002

Data Index: 603840 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2007. Min Act: -0.0002

Data Index: 964458 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1903. Min Act: -0.0002

Data Index: 703587 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1904. Min Act: -0.0002

Data Index: 1053161 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1065012 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1860. Min Act: -0.0002

Data Index: 1215628 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1757. Min Act: -0.0002

Data Index: 1145089 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1801. Min Act: -0.0002

Data Index: 1200980 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1728. Min Act: -0.0002

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1782. Min Act: -0.0002

Data Index: 677401 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1766. Min Act: -0.0002

Data Index: 133412 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1193298 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1147519 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1745. Min Act: -0.0002

Data Index: 234758 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1281074 (C4 (Web Text))

Max Activating Token Index: 763