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

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

Neuron 5117 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: 0.0922. Min Range: -0.0922

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1431259 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0852. Min Act: -0.0002

Data Index: 909695 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0922. Min Act: -0.0002

Data Index: 186930 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0848. Min Act: -0.0002

Data Index: 980496 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1055032 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0851. Min Act: -0.0002

Data Index: 433070 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0727. Min Act: -0.0002

Data Index: 395006 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0742. Min Act: -0.0002

Data Index: 779062 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1411720 (Python Code)

Max Activating Token Index: 889

Text #9

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1211585 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0724. Min Act: -0.0002

Data Index: 786298 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0788. Min Act: -0.0002

Data Index: 152248 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0823. Min Act: -0.0002

Data Index: 149837 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0713. Min Act: -0.0002

Data Index: 79785 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0683. Min Act: -0.0002

Data Index: 484270 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0663. Min Act: -0.0002

Data Index: 136112 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0709. Min Act: -0.0002

Data Index: 843030 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0708. Min Act: -0.0002

Data Index: 96420 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1585426 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.0922. Min Range: -0.0922

Max Act: 0.0838. Min Act: -0.0002

Data Index: 636462 (C4 (Web Text))

Max Activating Token Index: 656