Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3958 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0002

Data Index: 290720 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1311650 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0763. Min Act: -0.0001

Data Index: 900842 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1111545 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0815. Min Act: -0.0002

Data Index: 444963 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0746. Min Act: -0.0002

Data Index: 53847 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1288878 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1068015 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0766. Min Act: -0.0002

Data Index: 965163 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1250810 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1172160 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0732. Min Act: -0.0001

Data Index: 543363 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0754. Min Act: -0.0002

Data Index: 528431 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0804. Min Act: -0.0002

Data Index: 660609 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0771. Min Act: -0.0002

Data Index: 420147 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0701. Min Act: -0.0002

Data Index: 165508 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0712. Min Act: -0.0001

Data Index: 749267 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1119517 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1318897 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0675. Min Act: -0.0002

Data Index: 450390 (C4 (Web Text))

Max Activating Token Index: 198