Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 344 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.8478. Min Act: -0.0003

Data Index: 691788 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7744. Min Act: -0.0003

Data Index: 561672 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7843. Min Act: -0.0003

Data Index: 85963 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7381. Min Act: -0.0003

Data Index: 729070 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7583. Min Act: -0.0003

Data Index: 1311589 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.8239. Min Act: -0.0003

Data Index: 247471 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7033. Min Act: -0.0003

Data Index: 202649 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6563. Min Act: -0.0003

Data Index: 329703 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6739. Min Act: -0.0003

Data Index: 101672 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7033. Min Act: -0.0003

Data Index: 649466 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6769. Min Act: -0.0003

Data Index: 14112 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7442. Min Act: -0.0003

Data Index: 211105 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6310. Min Act: -0.0003

Data Index: 1076866 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6194. Min Act: -0.0003

Data Index: 919738 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6052. Min Act: -0.0003

Data Index: 1248403 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6723. Min Act: -0.0003

Data Index: 1162090 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.5319. Min Act: -0.0003

Data Index: 743143 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6244. Min Act: -0.0003

Data Index: 1314058 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7066. Min Act: -0.0003

Data Index: 660662 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6401. Min Act: -0.0003

Data Index: 1049194 (C4 (Web Text))

Max Activating Token Index: 300