Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2794 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.8309. Min Act: -0.0003

Data Index: 1157324 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6596. Min Act: -0.0003

Data Index: 1342627 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6822. Min Act: -0.0003

Data Index: 375757 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6781. Min Act: -0.0003

Data Index: 905941 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5920. Min Act: -0.0003

Data Index: 964855 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6308. Min Act: -0.0003

Data Index: 628877 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5900. Min Act: -0.0003

Data Index: 1038069 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6496. Min Act: -0.0003

Data Index: 550311 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6174. Min Act: -0.0003

Data Index: 1172733 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6301. Min Act: -0.0003

Data Index: 1174285 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5950. Min Act: -0.0003

Data Index: 1072062 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6264. Min Act: -0.0003

Data Index: 459536 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6192. Min Act: -0.0003

Data Index: 918951 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6080. Min Act: -0.0003

Data Index: 482131 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6226. Min Act: -0.0003

Data Index: 833866 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5828. Min Act: -0.0003

Data Index: 1051050 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5835. Min Act: -0.0003

Data Index: 1185524 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5088. Min Act: -0.0003

Data Index: 648963 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.6358. Min Act: -0.0003

Data Index: 1282545 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.8309. Min Range: -0.8309

Max Act: 0.5954. Min Act: -0.0003

Data Index: 496656 (C4 (Web Text))

Max Activating Token Index: 261