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

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

Neuron 887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1033. Min Range: -2.1033

Max Act: 2.1033. Min Act: -0.0000

Data Index: 942848 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.9040. Min Act: -0.0000

Data Index: 478924 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.8916. Min Act: -0.0000

Data Index: 685748 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.8146. Min Act: -0.0000

Data Index: 934006 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.8223. Min Act: -0.0000

Data Index: 310708 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.9845. Min Act: -0.0000

Data Index: 488353 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.6627. Min Act: -0.0000

Data Index: 558823 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7559. Min Act: -0.0000

Data Index: 336500 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.8598. Min Act: -0.0000

Data Index: 356293 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7554. Min Act: -0.0000

Data Index: 401713 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7318. Min Act: -0.0000

Data Index: 609991 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7262. Min Act: -0.0000

Data Index: 509351 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.8490. Min Act: -0.0000

Data Index: 161371 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7243. Min Act: -0.0000

Data Index: 285957 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7936. Min Act: -0.0000

Data Index: 489794 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1317003 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.5404. Min Act: -0.0000

Data Index: 747125 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.6265. Min Act: -0.0000

Data Index: 339901 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1058093 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 2.1033. Min Range: -2.1033

Max Act: 1.6096. Min Act: -0.0000

Data Index: 1054022 (C4 (Web Text))

Max Activating Token Index: 14