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

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

Neuron 1146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2343. Min Range: -2.2343

Max Act: 2.2343. Min Act: -0.0000

Data Index: 228300 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 2.2343. Min Range: -2.2343

Max Act: 2.1875. Min Act: -0.0000

Data Index: 806471 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.7811. Min Act: -0.0000

Data Index: 487733 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.9412. Min Act: -0.0000

Data Index: 359561 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.9359. Min Act: -0.0000

Data Index: 321797 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1388265 (Python Code)

Max Activating Token Index: 433

Text #6

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.8620. Min Act: -0.0000

Data Index: 745368 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.7873. Min Act: -0.0000

Data Index: 350184 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.8385. Min Act: -0.0000

Data Index: 614424 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1149639 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.6743. Min Act: -0.0000

Data Index: 1043887 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.5690. Min Act: -0.0000

Data Index: 965695 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.7615. Min Act: 0.0000

Data Index: 1485109 (Python Code)

Max Activating Token Index: 130

Text #13

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1344593 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.4839. Min Act: -0.0000

Data Index: 957448 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.5265. Min Act: -0.0000

Data Index: 980347 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.5968. Min Act: -0.0000

Data Index: 1617034 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.4365. Min Act: -0.0000

Data Index: 457416 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.4556. Min Act: -0.0000

Data Index: 46729 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 2.2343. Min Range: -2.2343

Max Act: 1.5846. Min Act: -0.0000

Data Index: 402645 (C4 (Web Text))

Max Activating Token Index: 538