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

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

Neuron 4740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: -0.0000

Data Index: 862574 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5022. Min Act: -0.0000

Data Index: 155268 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5006. Min Act: -0.0000

Data Index: 681212 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4756. Min Act: -0.0000

Data Index: 245680 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4698. Min Act: -0.0000

Data Index: 593520 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1231333 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4587. Min Act: -0.0000

Data Index: 700670 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4279. Min Act: -0.0000

Data Index: 504756 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1177471 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4355. Min Act: -0.0000

Data Index: 770636 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4401. Min Act: -0.0000

Data Index: 389016 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1143725 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1044772 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4039. Min Act: -0.0000

Data Index: 184813 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1121829 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1355390 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4243. Min Act: -0.0000

Data Index: 839086 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4268. Min Act: -0.0000

Data Index: 899038 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1292873 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4107. Min Act: -0.0000

Data Index: 569764 (C4 (Web Text))

Max Activating Token Index: 63