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

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

Neuron 596 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0180. Min Act: -0.0000

Data Index: 1127853 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.1264. Min Act: -0.0000

Data Index: 837551 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1166179 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0043. Min Act: -0.0000

Data Index: 405421 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9935. Min Act: -0.0000

Data Index: 623393 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0055. Min Act: -0.0000

Data Index: 1228754 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9861. Min Act: -0.0000

Data Index: 92604 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9836. Min Act: -0.0000

Data Index: 687778 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0155. Min Act: -0.0000

Data Index: 517412 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1237020 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9100. Min Act: -0.0000

Data Index: 456587 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9045. Min Act: -0.0000

Data Index: 426799 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.7888. Min Act: -0.0000

Data Index: 393453 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8647. Min Act: -0.0000

Data Index: 413477 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8477. Min Act: -0.0000

Data Index: 1178227 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9522. Min Act: -0.0000

Data Index: 689957 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9440. Min Act: -0.0000

Data Index: 698496 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1087078 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8376. Min Act: -0.0000

Data Index: 775929 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8249. Min Act: -0.0000

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 176