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

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

Neuron 2339 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: 1.2693. Min Range: -1.2693

Max Act: 1.2693. Min Act: -0.0000

Data Index: 724942 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0855. Min Act: -0.0000

Data Index: 672382 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1292. Min Act: -0.0000

Data Index: 3406 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1007. Min Act: -0.0000

Data Index: 908166 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.8577. Min Act: -0.0000

Data Index: 871813 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1193. Min Act: -0.0000

Data Index: 169844 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1037. Min Act: -0.0000

Data Index: 524097 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1607. Min Act: -0.0000

Data Index: 854187 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0599. Min Act: -0.0000

Data Index: 16232 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0428. Min Act: -0.0000

Data Index: 710989 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0875. Min Act: -0.0000

Data Index: 352172 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1000164 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.9363. Min Act: -0.0000

Data Index: 867079 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1130. Min Act: -0.0000

Data Index: 98781 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0528. Min Act: -0.0000

Data Index: 826333 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.9859. Min Act: -0.0000

Data Index: 987142 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0483. Min Act: -0.0000

Data Index: 346701 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.2693. Min Range: -1.2693

Max Act: 0.6068. Min Act: -0.0000

Data Index: 343490 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1280041 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.2693. Min Range: -1.2693

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1033212 (C4 (Web Text))

Max Activating Token Index: 669