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

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

Neuron 1806 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: 1.1228. Min Range: -1.1228

Max Act: 1.1123. Min Act: -0.0001

Data Index: 191639 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.1228. Min Act: -0.0001

Data Index: 455026 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0558. Min Act: -0.0001

Data Index: 911218 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0969. Min Act: -0.0001

Data Index: 1050310 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0961. Min Act: -0.0001

Data Index: 930376 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0420. Min Act: -0.0001

Data Index: 998557 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.1228. Min Range: -1.1228

Max Act: 1.0233. Min Act: -0.0001

Data Index: 367712 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9951. Min Act: -0.0001

Data Index: 1196534 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8970. Min Act: -0.0001

Data Index: 705537 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1233231 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9898. Min Act: -0.0001

Data Index: 1031276 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9596. Min Act: -0.0001

Data Index: 195354 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9483. Min Act: -0.0001

Data Index: 877161 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9384. Min Act: -0.0001

Data Index: 923299 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8884. Min Act: -0.0001

Data Index: 375879 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9752. Min Act: -0.0001

Data Index: 612755 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9028. Min Act: -0.0001

Data Index: 939993 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9007. Min Act: -0.0001

Data Index: 989469 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1310038 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.1228. Min Range: -1.1228

Max Act: 0.9509. Min Act: -0.0001

Data Index: 656994 (C4 (Web Text))

Max Activating Token Index: 743