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

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

Neuron 3072 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0777. Min Act: -0.0002

Data Index: 811243 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0732. Min Act: -0.0002

Data Index: 129660 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0706. Min Act: -0.0002

Data Index: 888494 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0748. Min Act: -0.0002

Data Index: 544815 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0715. Min Act: -0.0002

Data Index: 86557 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1024078 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0714. Min Act: -0.0002

Data Index: 375245 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0638. Min Act: -0.0002

Data Index: 467976 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0640. Min Act: -0.0002

Data Index: 58664 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0672. Min Act: -0.0002

Data Index: 532658 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1258824 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0704. Min Act: -0.0002

Data Index: 374847 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0733. Min Act: -0.0002

Data Index: 36468 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1349897 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0668. Min Act: -0.0002

Data Index: 619401 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1145624 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1287055 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0716. Min Act: -0.0002

Data Index: 544875 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0679. Min Act: -0.0002

Data Index: 46966 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.0777. Min Range: -0.0777

Max Act: 0.0662. Min Act: -0.0002

Data Index: 323668 (C4 (Web Text))

Max Activating Token Index: 56