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

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

Neuron 1300 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.3259. Min Act: -0.0001

Data Index: 275382 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.0661. Min Act: -0.0001

Data Index: 955724 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8731. Min Act: -0.0001

Data Index: 771857 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.9111. Min Act: -0.0001

Data Index: 588427 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8765. Min Act: -0.0001

Data Index: 104106 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.9122. Min Act: -0.0001

Data Index: 1081065 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.9737. Min Act: -0.0001

Data Index: 1016927 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8308. Min Act: -0.0001

Data Index: 1040114 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7939. Min Act: -0.0001

Data Index: 61529 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8722. Min Act: -0.0001

Data Index: 741709 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1285826 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8146. Min Act: -0.0001

Data Index: 846083 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8630. Min Act: -0.0001

Data Index: 617093 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7958. Min Act: -0.0001

Data Index: 837619 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8420. Min Act: -0.0001

Data Index: 960826 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.8734. Min Act: -0.0001

Data Index: 882970 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7418. Min Act: -0.0001

Data Index: 242946 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1298740 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7264. Min Act: -0.0001

Data Index: 994059 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 1.3259. Min Range: -1.3259

Max Act: 0.7744. Min Act: -0.0001

Data Index: 329602 (C4 (Web Text))

Max Activating Token Index: 756