Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 293 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0927. Min Act: -0.0002

Data Index: 404858 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0002

Data Index: 513135 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0002

Data Index: 601696 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0769. Min Act: -0.0002

Data Index: 56714 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0771. Min Act: -0.0002

Data Index: 592638 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1259277 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0756. Min Act: -0.0001

Data Index: 596187 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0763. Min Act: -0.0002

Data Index: 814906 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1077811 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0758. Min Act: -0.0002

Data Index: 644121 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1025848 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0741. Min Act: -0.0002

Data Index: 840559 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0749. Min Act: -0.0002

Data Index: 823930 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0711. Min Act: -0.0002

Data Index: 272 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1085658 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0705. Min Act: -0.0002

Data Index: 895974 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0688. Min Act: -0.0002

Data Index: 890977 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0714. Min Act: -0.0002

Data Index: 2510 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0706. Min Act: -0.0002

Data Index: 250764 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0710. Min Act: -0.0002

Data Index: 72175 (C4 (Web Text))

Max Activating Token Index: 886