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

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

Neuron 4532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.1837. Min Act: -0.0002

Data Index: 918820 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.2696. Min Act: -0.0002

Data Index: 1096442 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0968. Min Act: -0.0002

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.1214. Min Act: -0.0002

Data Index: 318484 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0940. Min Act: -0.0002

Data Index: 115120 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.1214. Min Act: -0.0002

Data Index: 906099 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.1461. Min Act: -0.0002

Data Index: 227345 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0595. Min Act: -0.0002

Data Index: 773108 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.9511. Min Act: -0.0002

Data Index: 749081 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0012. Min Act: -0.0002

Data Index: 950289 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.9090. Min Act: -0.0002

Data Index: 855393 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0003. Min Act: -0.0002

Data Index: 1059598 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0588. Min Act: -0.0002

Data Index: 11283 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.8949. Min Act: -0.0002

Data Index: 102074 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.9458. Min Act: -0.0002

Data Index: 979579 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.7930. Min Act: -0.0002

Data Index: 1252618 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.9930. Min Act: -0.0002

Data Index: 771131 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0397. Min Act: -0.0002

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.2696. Min Range: -1.2696

Max Act: 0.9433. Min Act: -0.0002

Data Index: 932697 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.2696. Min Range: -1.2696

Max Act: 1.0224. Min Act: -0.0002

Data Index: 460725 (C4 (Web Text))

Max Activating Token Index: 634