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

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

Neuron 199 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: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0002

Data Index: 597015 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0711. Min Act: -0.0002

Data Index: 50350 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1097136 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1161499 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0666. Min Act: -0.0002

Data Index: 66444 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1024155 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0661. Min Act: -0.0002

Data Index: 193218 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0650. Min Act: -0.0000

Data Index: 90814 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0644. Min Act: -0.0001

Data Index: 290663 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0628. Min Act: -0.0002

Data Index: 543895 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0642. Min Act: -0.0002

Data Index: 916656 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1260111 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0616. Min Act: -0.0002

Data Index: 86516 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0616. Min Act: -0.0002

Data Index: 277669 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0628. Min Act: -0.0002

Data Index: 956339 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1221838 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1298997 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0613. Min Act: -0.0002

Data Index: 506654 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0602. Min Act: -0.0001

Data Index: 189756 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0604. Min Act: -0.0000

Data Index: 747459 (C4 (Web Text))

Max Activating Token Index: 474