Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0001

Data Index: 724093 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0923. Min Act: -0.0001

Data Index: 817149 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0888. Min Act: -0.0001

Data Index: 357738 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0869. Min Act: -0.0001

Data Index: 486380 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0868. Min Act: -0.0001

Data Index: 219764 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0799. Min Act: -0.0001

Data Index: 716529 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0820. Min Act: -0.0001

Data Index: 569658 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1086079 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1140194 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1107159 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0705. Min Act: -0.0001

Data Index: 747201 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0734. Min Act: -0.0001

Data Index: 774873 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1105757 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0684. Min Act: -0.0001

Data Index: 13797 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1134060 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0679. Min Act: -0.0001

Data Index: 279876 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0730. Min Act: -0.0001

Data Index: 746363 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0700. Min Act: -0.0001

Data Index: 419587 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0675. Min Act: -0.0001

Data Index: 431226 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0725. Min Act: -0.0001

Data Index: 27568 (C4 (Web Text))

Max Activating Token Index: 832