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

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

Neuron 1578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0001

Data Index: 52701 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1860. Min Act: -0.0001

Data Index: 503746 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1850. Min Act: -0.0001

Data Index: 334962 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1899. Min Act: -0.0001

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1809. Min Act: -0.0001

Data Index: 450584 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1264015 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1604. Min Act: -0.0001

Data Index: 610897 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1548. Min Act: -0.0001

Data Index: 258480 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1575. Min Act: -0.0001

Data Index: 301975 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1448. Min Act: -0.0001

Data Index: 41762 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1440. Min Act: -0.0001

Data Index: 411677 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1111321 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1444. Min Act: -0.0001

Data Index: 184086 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1405. Min Act: -0.0001

Data Index: 845037 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1159765 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1311026 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1380. Min Act: -0.0001

Data Index: 969528 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1161122 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1331. Min Act: -0.0001

Data Index: 343785 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1280167 (C4 (Web Text))

Max Activating Token Index: 158