Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1663 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0617. Min Range: -1.0617

Max Act: 1.0617. Min Act: -0.0000

Data Index: 436908 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.8237. Min Act: 0.0000

Data Index: 1106999 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1356156 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7897. Min Act: -0.0000

Data Index: 874202 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7456. Min Act: 0.0000

Data Index: 662827 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7213. Min Act: -0.0000

Data Index: 658013 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7293. Min Act: -0.0000

Data Index: 466970 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7276. Min Act: -0.0000

Data Index: 911587 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1077463 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7537. Min Act: 0.0000

Data Index: 1354256 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6779. Min Act: -0.0000

Data Index: 584788 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.7380. Min Act: 0.0000

Data Index: 910532 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6978. Min Act: -0.0000

Data Index: 424646 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1336891 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6588. Min Act: -0.0000

Data Index: 810696 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6754. Min Act: 0.0001

Data Index: 986207 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6363. Min Act: -0.0000

Data Index: 986514 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6963. Min Act: -0.0000

Data Index: 892957 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6467. Min Act: -0.0000

Data Index: 618390 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.0617. Min Range: -1.0617

Max Act: 0.6664. Min Act: -0.0000

Data Index: 207730 (C4 (Web Text))

Max Activating Token Index: 913