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

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

Neuron 1074 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.7245. Min Act: -0.0000

Data Index: 480859 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4820. Min Act: -0.0000

Data Index: 588931 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5605. Min Act: 0.0000

Data Index: 358993 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.2699. Min Act: -0.0000

Data Index: 54806 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1193157 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0817. Min Act: -0.0000

Data Index: 558887 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.2992. Min Act: -0.0000

Data Index: 689092 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.1212. Min Act: -0.0000

Data Index: 726136 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.1971. Min Act: -0.0000

Data Index: 915214 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1302293 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3281. Min Act: -0.0000

Data Index: 295491 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0307. Min Act: -0.0000

Data Index: 1223389 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.1180. Min Act: -0.0000

Data Index: 610747 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1229438 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0999. Min Act: -0.0000

Data Index: 411375 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1206248 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0728. Min Act: -0.0000

Data Index: 346641 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0500. Min Act: -0.0000

Data Index: 399545 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1356787 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.0473. Min Act: -0.0000

Data Index: 567778 (C4 (Web Text))

Max Activating Token Index: 534