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

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

Neuron 4104 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: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0002

Data Index: 2630 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0807. Min Act: -0.0002

Data Index: 64588 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0783. Min Act: -0.0002

Data Index: 476911 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0733. Min Act: -0.0002

Data Index: 43838 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1114735 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0681. Min Act: -0.0002

Data Index: 710740 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1300126 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0592. Min Act: -0.0002

Data Index: 695809 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0665. Min Act: -0.0002

Data Index: 166733 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1215852 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1132899 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0636. Min Act: -0.0002

Data Index: 706180 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1084454 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0688. Min Act: -0.0002

Data Index: 331856 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0659. Min Act: -0.0002

Data Index: 973080 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0651. Min Act: -0.0002

Data Index: 272690 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1172242 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0583. Min Act: -0.0002

Data Index: 127309 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0594. Min Act: -0.0002

Data Index: 836224 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0634. Min Act: -0.0002

Data Index: 358127 (C4 (Web Text))

Max Activating Token Index: 734