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

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

Neuron 1651 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0003

Data Index: 616705 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1300517 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0764. Min Act: -0.0002

Data Index: 653306 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0797. Min Act: -0.0003

Data Index: 652071 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0791. Min Act: -0.0002

Data Index: 745929 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1119047 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0782. Min Act: -0.0003

Data Index: 262931 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0767. Min Act: -0.0003

Data Index: 209540 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0766. Min Act: -0.0003

Data Index: 881029 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0798. Min Act: -0.0003

Data Index: 702169 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1133347 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0718. Min Act: -0.0002

Data Index: 468562 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0747. Min Act: -0.0003

Data Index: 479093 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1016694 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0724. Min Act: -0.0003

Data Index: 1471418 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1035703 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1171186 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1327723 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1023162 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1100274 (C4 (Web Text))

Max Activating Token Index: 949