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

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

Neuron 762 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0002

Data Index: 88496 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0858. Min Act: -0.0001

Data Index: 746324 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0794. Min Act: -0.0002

Data Index: 128017 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0756. Min Act: -0.0002

Data Index: 282072 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0794. Min Act: -0.0002

Data Index: 575244 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1072183 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0764. Min Act: -0.0002

Data Index: 755968 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0812. Min Act: -0.0002

Data Index: 946228 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1358994 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0813. Min Act: -0.0002

Data Index: 785015 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0778. Min Act: -0.0001

Data Index: 27509 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0839. Min Act: -0.0001

Data Index: 660439 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0774. Min Act: -0.0002

Data Index: 6126 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0792. Min Act: -0.0002

Data Index: 451326 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1131510 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0714. Min Act: -0.0002

Data Index: 539396 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0709. Min Act: -0.0002

Data Index: 501799 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1171554 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0768. Min Act: -0.0002

Data Index: 736965 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1209798 (C4 (Web Text))

Max Activating Token Index: 185