Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 511 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0002

Data Index: 330073 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0844. Min Act: -0.0002

Data Index: 714603 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0826. Min Act: -0.0002

Data Index: 781541 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0832. Min Act: -0.0002

Data Index: 706283 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0806. Min Act: -0.0002

Data Index: 515202 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0794. Min Act: -0.0002

Data Index: 973395 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0747. Min Act: -0.0002

Data Index: 766096 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0764. Min Act: -0.0002

Data Index: 779572 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1170786 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0755. Min Act: -0.0002

Data Index: 115376 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1108995 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1151041 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0751. Min Act: -0.0002

Data Index: 182220 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0702. Min Act: -0.0002

Data Index: 764458 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1163989 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1129875 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1182391 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0667. Min Act: -0.0002

Data Index: 927930 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0680. Min Act: -0.0002

Data Index: 769504 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0656. Min Act: -0.0002

Data Index: 251489 (C4 (Web Text))

Max Activating Token Index: 197