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

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

Neuron 4251 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: 0.0735. Min Range: -0.0735

Max Act: 0.0696. Min Act: -0.0002

Data Index: 87855 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0002

Data Index: 809079 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1002821 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0666. Min Act: -0.0002

Data Index: 686520 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0696. Min Act: -0.0002

Data Index: 607456 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0713. Min Act: -0.0002

Data Index: 611995 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1166411 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1263289 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1205061 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0665. Min Act: -0.0002

Data Index: 937785 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0666. Min Act: -0.0002

Data Index: 292733 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0655. Min Act: -0.0002

Data Index: 559714 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0648. Min Act: -0.0002

Data Index: 34543 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0653. Min Act: -0.0002

Data Index: 149514 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0656. Min Act: -0.0002

Data Index: 410036 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0656. Min Act: -0.0002

Data Index: 44956 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0636. Min Act: -0.0002

Data Index: 583749 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0631. Min Act: -0.0002

Data Index: 264017 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0654. Min Act: -0.0002

Data Index: 855729 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0629. Min Act: -0.0002

Data Index: 259960 (C4 (Web Text))

Max Activating Token Index: 438