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

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

Neuron 3896 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2140. Min Act: -0.0000

Data Index: 300268 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2048. Min Act: -0.0000

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1750. Min Act: -0.0000

Data Index: 610975 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1976. Min Act: -0.0000

Data Index: 11787 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2031. Min Act: -0.0000

Data Index: 816274 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1853. Min Act: -0.0000

Data Index: 589940 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1118627 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1191975 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1927. Min Act: -0.0000

Data Index: 868910 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1976. Min Act: -0.0000

Data Index: 9592 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1760. Min Act: -0.0000

Data Index: 679960 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1845. Min Act: -0.0000

Data Index: 580592 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1739. Min Act: -0.0000

Data Index: 436947 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1800. Min Act: -0.0000

Data Index: 109255 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1828. Min Act: -0.0000

Data Index: 266827 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1793. Min Act: -0.0000

Data Index: 670179 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1974. Min Act: -0.0000

Data Index: 559606 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1168931 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1651. Min Act: -0.0000

Data Index: 573003 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 754