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

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

Neuron 3190 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: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0002

Data Index: 957228 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0770. Min Act: -0.0002

Data Index: 87246 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0761. Min Act: -0.0002

Data Index: 319051 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0766. Min Act: -0.0002

Data Index: 110777 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1040499 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0754. Min Act: -0.0002

Data Index: 759840 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0716. Min Act: -0.0002

Data Index: 459592 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0686. Min Act: -0.0002

Data Index: 422045 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0702. Min Act: -0.0002

Data Index: 774127 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0697. Min Act: -0.0002

Data Index: 168048 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0666. Min Act: -0.0002

Data Index: 503352 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0667. Min Act: -0.0002

Data Index: 423791 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0668. Min Act: -0.0002

Data Index: 243354 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0670. Min Act: -0.0002

Data Index: 82566 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0612. Min Act: -0.0002

Data Index: 184384 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0676. Min Act: -0.0002

Data Index: 133709 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1155806 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1173790 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0685. Min Act: -0.0002

Data Index: 876890 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0624. Min Act: -0.0002

Data Index: 354182 (C4 (Web Text))

Max Activating Token Index: 875