Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3319 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0001

Data Index: 811343 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0806. Min Act: -0.0000

Data Index: 610600 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1065959 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0724. Min Act: -0.0000

Data Index: 970625 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1130729 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1054830 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0686. Min Act: -0.0001

Data Index: 769422 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0654. Min Act: -0.0001

Data Index: 225651 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0646. Min Act: -0.0001

Data Index: 79908 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0674. Min Act: -0.0000

Data Index: 586023 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0624. Min Act: -0.0001

Data Index: 351359 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0635. Min Act: -0.0001

Data Index: 330902 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1099883 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0584. Min Act: -0.0001

Data Index: 716890 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0618. Min Act: -0.0001

Data Index: 701736 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0569. Min Act: -0.0001

Data Index: 822318 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0611. Min Act: -0.0001

Data Index: 179591 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0568. Min Act: -0.0000

Data Index: 455503 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0602. Min Act: -0.0001

Data Index: 725428 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1319410 (C4 (Web Text))

Max Activating Token Index: 520