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

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

Neuron 1834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.6089. Min Act: -0.0000

Data Index: 305786 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.6017. Min Act: -0.0000

Data Index: 621178 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5844. Min Act: -0.0000

Data Index: 489893 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5417. Min Act: -0.0000

Data Index: 36166 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1144163 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5240. Min Act: -0.0000

Data Index: 736001 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1245851 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5098. Min Act: -0.0000

Data Index: 683507 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1122423 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4864. Min Act: -0.0000

Data Index: 620338 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1343188 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1217007 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4833. Min Act: -0.0000

Data Index: 579112 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4410. Min Act: -0.0000

Data Index: 400972 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4383. Min Act: -0.0000

Data Index: 68264 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1283258 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4371. Min Act: -0.0000

Data Index: 635271 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4491. Min Act: -0.0000

Data Index: 644543 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4502. Min Act: -0.0000

Data Index: 898405 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.6089. Min Range: -0.6089

Max Act: 0.4282. Min Act: -0.0000

Data Index: 58206 (C4 (Web Text))

Max Activating Token Index: 173