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

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

Neuron 1788 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0766. Min Act: -0.0005

Data Index: 539063 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0787. Min Act: -0.0005

Data Index: 989698 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0765. Min Act: -0.0005

Data Index: 854233 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0005

Data Index: 1246315 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0745. Min Act: -0.0005

Data Index: 590871 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0751. Min Act: -0.0005

Data Index: 1282184 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0736. Min Act: -0.0005

Data Index: 1655609 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0711. Min Act: -0.0005

Data Index: 129914 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0704. Min Act: -0.0005

Data Index: 993165 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0615. Min Act: -0.0005

Data Index: 1348212 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0726. Min Act: -0.0005

Data Index: 795273 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0650. Min Act: -0.0005

Data Index: 496158 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0674. Min Act: -0.0005

Data Index: 137295 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0643. Min Act: -0.0005

Data Index: 1091079 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0666. Min Act: -0.0005

Data Index: 73986 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0695. Min Act: -0.0005

Data Index: 883022 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0668. Min Act: -0.0005

Data Index: 191519 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0661. Min Act: -0.0005

Data Index: 744146 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0624. Min Act: -0.0005

Data Index: 1392544 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0664. Min Act: -0.0005

Data Index: 661646 (C4 (Web Text))

Max Activating Token Index: 757