Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1649 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1815. Min Act: -0.0001

Data Index: 662687 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1314982 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1661. Min Act: -0.0001

Data Index: 273708 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1589. Min Act: -0.0001

Data Index: 331110 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1754. Min Act: -0.0001

Data Index: 313079 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1709. Min Act: -0.0001

Data Index: 735426 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1344006 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1555. Min Act: -0.0001

Data Index: 650341 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1496. Min Act: -0.0001

Data Index: 466128 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1654. Min Act: -0.0001

Data Index: 750681 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1533. Min Act: -0.0001

Data Index: 182850 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1414. Min Act: -0.0001

Data Index: 804239 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1333816 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1033218 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1112524 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1445. Min Act: -0.0001

Data Index: 335961 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1432. Min Act: -0.0001

Data Index: 381659 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1475. Min Act: -0.0001

Data Index: 136473 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1475. Min Act: -0.0001

Data Index: 89299 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1372. Min Act: -0.0001

Data Index: 178431 (C4 (Web Text))

Max Activating Token Index: 538