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

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

Neuron 2760 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0003

Data Index: 808363 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0662. Min Act: -0.0002

Data Index: 292515 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0657. Min Act: -0.0003

Data Index: 904855 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0647. Min Act: -0.0003

Data Index: 449374 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0643. Min Act: -0.0003

Data Index: 315272 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0633. Min Act: -0.0003

Data Index: 975346 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1023722 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1328307 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0602. Min Act: -0.0003

Data Index: 10894 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0614. Min Act: -0.0003

Data Index: 839915 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0585. Min Act: -0.0002

Data Index: 617897 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0612. Min Act: -0.0003

Data Index: 120454 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0609. Min Act: -0.0003

Data Index: 84993 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0603. Min Act: -0.0002

Data Index: 773940 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0584. Min Act: -0.0003

Data Index: 943688 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1169375 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0577. Min Act: -0.0002

Data Index: 98631 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0581. Min Act: -0.0003

Data Index: 637425 (C4 (Web Text))

Max Activating Token Index: 500