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

Dataset: The Pile

Neuron 1796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1492. Min Act: -0.0000

Data Index: 629792 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9316. Min Act: -0.0000

Data Index: 211758 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9069. Min Act: -0.0000

Data Index: 225897 (The Pile)

Max Activating Token Index: 866

Text #3

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1156493 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1046561 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1179586 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1836633 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8637. Min Act: -0.0000

Data Index: 867093 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8800. Min Act: -0.0000

Data Index: 67686 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1762410 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1812987 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1373017 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8394. Min Act: -0.0000

Data Index: 82156 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1979915 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7774. Min Act: -0.0000

Data Index: 547188 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1452982 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1935304 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8039. Min Act: -0.0000

Data Index: 696626 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1552211 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8080. Min Act: -0.0000

Data Index: 988989 (The Pile)

Max Activating Token Index: 268