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

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

Neuron 460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2174. Min Act: -0.0001

Data Index: 299899 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1294004 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2131. Min Act: -0.0001

Data Index: 478828 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2133. Min Act: -0.0001

Data Index: 702086 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1240874 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2060. Min Act: -0.0001

Data Index: 345219 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2076. Min Act: -0.0001

Data Index: 105312 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1318829 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1838. Min Act: -0.0001

Data Index: 897969 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2056. Min Act: -0.0001

Data Index: 473615 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1142254 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2114. Min Act: -0.0001

Data Index: 361428 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1966. Min Act: -0.0001

Data Index: 618312 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1996. Min Act: -0.0001

Data Index: 289607 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1512393 (Python Code)

Max Activating Token Index: 362

Text #15

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1982. Min Act: -0.0001

Data Index: 164140 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1912. Min Act: -0.0001

Data Index: 959836 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1966. Min Act: -0.0001

Data Index: 496488 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2047. Min Act: -0.0001

Data Index: 122696 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1834. Min Act: -0.0001

Data Index: 608266 (C4 (Web Text))

Max Activating Token Index: 68