Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0002

Data Index: 568605 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0778. Min Act: -0.0002

Data Index: 360571 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0702. Min Act: -0.0002

Data Index: 957979 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1131081 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0705. Min Act: -0.0002

Data Index: 388100 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1316330 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0694. Min Act: -0.0002

Data Index: 694365 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0671. Min Act: -0.0002

Data Index: 94944 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1280976 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0721. Min Act: -0.0002

Data Index: 532335 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0718. Min Act: -0.0002

Data Index: 744879 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1023461 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0690. Min Act: -0.0002

Data Index: 828318 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1136642 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1244867 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0652. Min Act: -0.0002

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0659. Min Act: -0.0002

Data Index: 864265 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0621. Min Act: -0.0002

Data Index: 206236 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0653. Min Act: -0.0002

Data Index: 858200 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0598. Min Act: -0.0002

Data Index: 428355 (C4 (Web Text))

Max Activating Token Index: 328