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

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

Neuron 1371 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.9828. Min Act: -0.0000

Data Index: 792641 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.8191. Min Act: -0.0000

Data Index: 1103953 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 10.1436. Min Range: -10.1436

Max Act: 10.0423. Min Act: -0.0000

Data Index: 1240807 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 10.1436. Min Range: -10.1436

Max Act: 10.1436. Min Act: -0.0000

Data Index: 320913 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 10.1436. Min Range: -10.1436

Max Act: 10.0535. Min Act: -0.0000

Data Index: 24241 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.0906. Min Act: -0.0000

Data Index: 1041229 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.7278. Min Act: 0.0000

Data Index: 58700 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.8033. Min Act: -0.0000

Data Index: 791764 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.2954. Min Act: -0.0000

Data Index: 1332255 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.5219. Min Act: -0.0000

Data Index: 188820 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.1729. Min Act: -0.0000

Data Index: 363520 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.5745. Min Act: 0.0000

Data Index: 1258839 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.9613. Min Act: -0.0000

Data Index: 862377 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.5051. Min Act: -0.0000

Data Index: 312807 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.1132. Min Act: -0.0000

Data Index: 527571 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.6266. Min Act: -0.0000

Data Index: 1229069 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.2363. Min Act: -0.0000

Data Index: 1149542 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.6895. Min Act: -0.0000

Data Index: 740156 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 10.1436. Min Range: -10.1436

Max Act: 9.0945. Min Act: -0.0000

Data Index: 191391 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 10.1436. Min Range: -10.1436

Max Act: 8.0390. Min Act: 0.0000

Data Index: 1170774 (C4 (Web Text))

Max Activating Token Index: 141