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

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

Neuron 3620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.6172. Min Act: -0.0000

Data Index: 636459 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2931. Min Act: -0.0000

Data Index: 190771 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.3803. Min Act: -0.0000

Data Index: 903272 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2908. Min Act: -0.0000

Data Index: 311664 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2889. Min Act: -0.0000

Data Index: 755164 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.3651. Min Act: -0.0000

Data Index: 887471 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.1852. Min Act: -0.0000

Data Index: 850444 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2155. Min Act: -0.0000

Data Index: 487239 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2287. Min Act: -0.0000

Data Index: 846817 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2242. Min Act: -0.0000

Data Index: 762951 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2460. Min Act: -0.0000

Data Index: 200312 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2413. Min Act: -0.0000

Data Index: 184573 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.2282. Min Act: -0.0000

Data Index: 142796 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.0757. Min Act: -0.0000

Data Index: 16397 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.1423. Min Act: -0.0000

Data Index: 799865 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.0669. Min Act: -0.0000

Data Index: 611517 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.0538. Min Act: -0.0000

Data Index: 903711 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.1260. Min Act: -0.0000

Data Index: 888118 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.1894. Min Act: -0.0000

Data Index: 961749 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.6172. Min Range: -1.6172

Max Act: 1.0460. Min Act: -0.0000

Data Index: 317807 (C4 (Web Text))

Max Activating Token Index: 152