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

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

Neuron 1727 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: 0.0829. Min Range: -0.0829

Max Act: 0.0826. Min Act: -0.0002

Data Index: 161417 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0002

Data Index: 481580 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0785. Min Act: -0.0002

Data Index: 296324 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1326603 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0733. Min Act: -0.0001

Data Index: 387785 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1013840 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0667. Min Act: -0.0002

Data Index: 289256 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1213500 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0703. Min Act: -0.0001

Data Index: 162370 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0687. Min Act: -0.0002

Data Index: 973324 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0659. Min Act: -0.0002

Data Index: 754306 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1308193 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0702. Min Act: -0.0001

Data Index: 622045 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0663. Min Act: -0.0002

Data Index: 510475 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1168865 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0636. Min Act: -0.0002

Data Index: 25068 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1007046 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0654. Min Act: -0.0002

Data Index: 251759 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0608. Min Act: -0.0002

Data Index: 743376 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1068576 (C4 (Web Text))

Max Activating Token Index: 319