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

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

Neuron 191 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.9343. Min Act: -0.0004

Data Index: 1315109 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8788. Min Act: -0.0004

Data Index: 642142 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8127. Min Act: -0.0004

Data Index: 1305811 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7805. Min Act: -0.0004

Data Index: 477736 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7127. Min Act: -0.0004

Data Index: 123667 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7326. Min Act: -0.0004

Data Index: 601538 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7904. Min Act: -0.0004

Data Index: 842479 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6646. Min Act: -0.0004

Data Index: 613722 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6637. Min Act: -0.0004

Data Index: 1163390 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7026. Min Act: -0.0004

Data Index: 350526 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7204. Min Act: -0.0004

Data Index: 766010 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7186. Min Act: -0.0004

Data Index: 994508 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7359. Min Act: -0.0004

Data Index: 233529 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7076. Min Act: -0.0004

Data Index: 1178757 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6675. Min Act: -0.0004

Data Index: 998785 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7326. Min Act: -0.0004

Data Index: 596499 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6664. Min Act: -0.0004

Data Index: 1015277 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7072. Min Act: -0.0004

Data Index: 973227 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6815. Min Act: -0.0004

Data Index: 873411 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.6816. Min Act: -0.0004

Data Index: 1177187 (C4 (Web Text))

Max Activating Token Index: 769