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

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

Neuron 3574 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: 0.8745. Min Range: -0.8745

Max Act: 0.8745. Min Act: -0.0000

Data Index: 800815 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1148322 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8081. Min Act: -0.0000

Data Index: 669274 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8101. Min Act: -0.0000

Data Index: 667263 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7812. Min Act: -0.0000

Data Index: 739134 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7517. Min Act: -0.0000

Data Index: 200439 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7524. Min Act: -0.0000

Data Index: 390836 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7385. Min Act: 0.0000

Data Index: 689488 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7377. Min Act: -0.0000

Data Index: 606060 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7332. Min Act: -0.0000

Data Index: 790459 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6843. Min Act: -0.0000

Data Index: 728480 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7300. Min Act: -0.0000

Data Index: 66139 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7155. Min Act: -0.0000

Data Index: 196541 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7199. Min Act: -0.0000

Data Index: 371304 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1289894 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7298. Min Act: -0.0000

Data Index: 292443 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6833. Min Act: -0.0000

Data Index: 598296 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6861. Min Act: -0.0000

Data Index: 277957 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7046. Min Act: -0.0000

Data Index: 276123 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1130716 (C4 (Web Text))

Max Activating Token Index: 336