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

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

Neuron 1700 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5914. Min Act: -0.0000

Data Index: 1118378 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5431. Min Act: -0.0001

Data Index: 858855 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1034525 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3906. Min Act: -0.0000

Data Index: 60603 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3993. Min Act: -0.0001

Data Index: 1126489 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1278561 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4489. Min Act: -0.0000

Data Index: 204543 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3684. Min Act: -0.0000

Data Index: 20463 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3974. Min Act: -0.0000

Data Index: 702632 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.4234. Min Act: -0.0001

Data Index: 203953 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3098. Min Act: -0.0000

Data Index: 459898 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3488. Min Act: -0.0001

Data Index: 1175776 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3399. Min Act: -0.0000

Data Index: 549712 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3239. Min Act: -0.0001

Data Index: 658500 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2930. Min Act: -0.0000

Data Index: 584016 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3990. Min Act: -0.0000

Data Index: 94441 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3495. Min Act: -0.0000

Data Index: 151980 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3744. Min Act: -0.0000

Data Index: 283004 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.3548. Min Act: -0.0000

Data Index: 851658 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.5914. Min Range: -1.5914

Max Act: 1.2993. Min Act: -0.0001

Data Index: 1146096 (C4 (Web Text))

Max Activating Token Index: 314