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

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

Neuron 1191 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: 1.3245. Min Range: -1.3245

Max Act: 1.0497. Min Act: -0.0004

Data Index: 512560 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1649. Min Act: -0.0004

Data Index: 525626 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1852. Min Act: -0.0004

Data Index: 906495 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0609. Min Act: -0.0004

Data Index: 687687 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1073. Min Act: -0.0004

Data Index: 1027567 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2388. Min Act: -0.0004

Data Index: 725775 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1906. Min Act: -0.0004

Data Index: 315894 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1893. Min Act: -0.0004

Data Index: 584632 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1211. Min Act: -0.0004

Data Index: 980699 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.3245. Min Range: -1.3245

Max Act: 0.9630. Min Act: -0.0004

Data Index: 875385 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2399. Min Act: -0.0004

Data Index: 322306 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2157. Min Act: -0.0004

Data Index: 72612 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1193. Min Act: -0.0004

Data Index: 1020004 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1483. Min Act: -0.0004

Data Index: 1328701 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.3245. Min Act: -0.0004

Data Index: 1061134 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2434. Min Act: -0.0004

Data Index: 465097 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1684. Min Act: -0.0004

Data Index: 1145857 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0369. Min Act: -0.0004

Data Index: 1058260 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1464. Min Act: -0.0004

Data Index: 281462 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1414. Min Act: -0.0004

Data Index: 1262181 (C4 (Web Text))

Max Activating Token Index: 311