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

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

Neuron 1317 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: 0.0826. Min Range: -0.0826

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1203698 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0002

Data Index: 594214 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0792. Min Act: -0.0002

Data Index: 484504 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0778. Min Act: -0.0002

Data Index: 449894 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0729. Min Act: -0.0002

Data Index: 718741 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0778. Min Act: -0.0002

Data Index: 391219 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0688. Min Act: -0.0002

Data Index: 297500 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0718. Min Act: -0.0002

Data Index: 515447 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0747. Min Act: -0.0002

Data Index: 781311 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0673. Min Act: -0.0002

Data Index: 429743 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0701. Min Act: -0.0002

Data Index: 584579 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1002650 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0660. Min Act: -0.0002

Data Index: 131771 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0702. Min Act: -0.0002

Data Index: 94182 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0662. Min Act: -0.0002

Data Index: 665035 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1245435 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0659. Min Act: -0.0002

Data Index: 747041 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0662. Min Act: -0.0002

Data Index: 801115 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0623. Min Act: -0.0002

Data Index: 499108 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0645. Min Act: -0.0002

Data Index: 58575 (C4 (Web Text))

Max Activating Token Index: 104