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

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

Neuron 4005 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: 0.6923. Min Range: -0.6923

Max Act: 0.6923. Min Act: -0.0000

Data Index: 198716 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1284120 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1350186 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6003. Min Act: -0.0000

Data Index: 899020 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5785. Min Act: -0.0000

Data Index: 566461 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5653. Min Act: -0.0000

Data Index: 319874 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5535. Min Act: -0.0000

Data Index: 181325 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1007050 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5680. Min Act: -0.0000

Data Index: 280689 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1268623 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5569. Min Act: -0.0000

Data Index: 867280 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5394. Min Act: -0.0000

Data Index: 442904 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5354. Min Act: -0.0000

Data Index: 414503 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5493. Min Act: -0.0000

Data Index: 951660 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5306. Min Act: -0.0000

Data Index: 377672 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1298556 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5013. Min Act: -0.0000

Data Index: 139709 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5304. Min Act: -0.0000

Data Index: 694749 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5098. Min Act: -0.0000

Data Index: 659310 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5264. Min Act: -0.0000

Data Index: 67142 (C4 (Web Text))

Max Activating Token Index: 988