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

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

Neuron 3522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.7692. Min Act: -0.0000

Data Index: 305017 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.7803. Min Act: -0.0000

Data Index: 393503 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.8267. Min Act: -0.0000

Data Index: 849225 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.7386. Min Act: -0.0000

Data Index: 942005 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1253391 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.7079. Min Act: -0.0000

Data Index: 13124 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6879. Min Act: -0.0000

Data Index: 818997 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1205918 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6421. Min Act: -0.0000

Data Index: 544723 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1141105 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6243. Min Act: -0.0000

Data Index: 114922 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6384. Min Act: -0.0000

Data Index: 300585 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6524. Min Act: -0.0000

Data Index: 863883 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6242. Min Act: -0.0000

Data Index: 983055 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6064. Min Act: -0.0000

Data Index: 558047 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6093. Min Act: -0.0000

Data Index: 199962 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1075576 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6137. Min Act: -0.0000

Data Index: 96365 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.6010. Min Act: -0.0000

Data Index: 314030 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.8267. Min Range: -0.8267

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1301622 (C4 (Web Text))

Max Activating Token Index: 88