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

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

Neuron 1004 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1722. Min Act: -0.0000

Data Index: 779101 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1186. Min Act: -0.0000

Data Index: 540209 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1236. Min Act: -0.0000

Data Index: 837999 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1194. Min Act: -0.0000

Data Index: 245529 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1113. Min Act: -0.0000

Data Index: 594907 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1099. Min Act: -0.0000

Data Index: 954806 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1027. Min Act: -0.0000

Data Index: 412757 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.1097. Min Act: -0.0000

Data Index: 245933 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1161787 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0978. Min Act: -0.0000

Data Index: 617164 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0908. Min Act: -0.0000

Data Index: 571589 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0932. Min Act: -0.0000

Data Index: 930340 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0864. Min Act: -0.0000

Data Index: 341556 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0889. Min Act: -0.0000

Data Index: 334752 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0814. Min Act: -0.0000

Data Index: 207539 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0878. Min Act: -0.0000

Data Index: 34374 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0748. Min Act: -0.0000

Data Index: 226764 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0907. Min Act: -0.0000

Data Index: 90750 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0796. Min Act: -0.0000

Data Index: 679341 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1722. Min Range: -0.1722

Max Act: 0.0817. Min Act: -0.0000

Data Index: 647030 (C4 (Web Text))

Max Activating Token Index: 956