Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 6 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.5040. Min Act: -0.0001

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.2212. Min Act: -0.0001

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.3558. Min Act: -0.0001

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.3592. Min Act: -0.0001

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.3344. Min Act: -0.0001

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1533. Min Act: -0.0001

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1326. Min Act: -0.0001

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1265. Min Act: -0.0001

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1328. Min Act: -0.0001

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.2399. Min Act: -0.0001

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.2187. Min Act: -0.0001

Data Index: 603915 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.0898. Min Act: -0.0001

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1986. Min Act: -0.0001

Data Index: 130618 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.0372. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.5040. Min Range: -3.5040

Max Act: 3.1035. Min Act: -0.0001

Data Index: 131202 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.5040. Min Range: -3.5040

Max Act: 2.9772. Min Act: -0.0001

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 3.5040. Min Range: -3.5040

Max Act: 2.9728. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 3.5040. Min Range: -3.5040

Max Act: 2.9357. Min Act: -0.0001

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.5040. Min Range: -3.5040

Max Act: 2.9504. Min Act: -0.0001

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 3.5040. Min Range: -3.5040

Max Act: 2.9441. Min Act: -0.0001

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 648