Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5472 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1342695 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0165. Min Act: -0.0000

Data Index: 497392 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1079590 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7921. Min Act: -0.0000

Data Index: 284170 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7868. Min Act: -0.0000

Data Index: 18476 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1077448 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7186. Min Act: -0.0000

Data Index: 56318 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7147. Min Act: -0.0000

Data Index: 98951 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7112. Min Act: -0.0000

Data Index: 380096 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7056. Min Act: -0.0000

Data Index: 304286 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1020144 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6501. Min Act: -0.0000

Data Index: 171183 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1175798 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6760. Min Act: -0.0000

Data Index: 19554 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6788. Min Act: -0.0000

Data Index: 393603 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.7198. Min Act: -0.0000

Data Index: 601188 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6257. Min Act: -0.0000

Data Index: 505791 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1304977 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6317. Min Act: -0.0000

Data Index: 265844 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.6407. Min Act: -0.0000

Data Index: 847610 (C4 (Web Text))

Max Activating Token Index: 504