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

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

Neuron 660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0838. Min Act: -0.0006

Data Index: 154383 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0006

Data Index: 839603 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0827. Min Act: -0.0006

Data Index: 1280583 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0789. Min Act: -0.0006

Data Index: 351529 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0806. Min Act: -0.0006

Data Index: 552874 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0796. Min Act: -0.0006

Data Index: 661034 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0799. Min Act: -0.0006

Data Index: 42995 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0788. Min Act: -0.0006

Data Index: 202801 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0805. Min Act: -0.0006

Data Index: 214398 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0799. Min Act: -0.0006

Data Index: 169741 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0748. Min Act: -0.0006

Data Index: 1031132 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0804. Min Act: -0.0006

Data Index: 66378 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0754. Min Act: -0.0006

Data Index: 447761 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0764. Min Act: -0.0006

Data Index: 42012 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0750. Min Act: -0.0006

Data Index: 871627 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0781. Min Act: -0.0006

Data Index: 849344 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0745. Min Act: -0.0006

Data Index: 612761 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0756. Min Act: -0.0006

Data Index: 1329687 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0760. Min Act: -0.0006

Data Index: 198381 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0727. Min Act: -0.0006

Data Index: 393451 (C4 (Web Text))

Max Activating Token Index: 179