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

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

Neuron 4162 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: 1.2170. Min Range: -1.2170

Max Act: 1.2170. Min Act: -0.0001

Data Index: 1634870 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.1060. Min Act: -0.0001

Data Index: 1396282 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.1824. Min Act: -0.0001

Data Index: 1539242 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.2147. Min Act: -0.0001

Data Index: 1569325 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1404362 (Python Code)

Max Activating Token Index: 377

Text #5

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.0636. Min Act: -0.0001

Data Index: 1436432 (Python Code)

Max Activating Token Index: 436

Text #6

Max Range: 1.2170. Min Range: -1.2170

Max Act: 1.0210. Min Act: -0.0001

Data Index: 1613390 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1409960 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9218. Min Act: -0.0001

Data Index: 1384418 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9441. Min Act: -0.0001

Data Index: 1386368 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9640. Min Act: -0.0001

Data Index: 1441644 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1545471 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9875. Min Act: -0.0001

Data Index: 1483324 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9480. Min Act: -0.0001

Data Index: 1559430 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1484584 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.8915. Min Act: -0.0001

Data Index: 1494925 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.9777. Min Act: -0.0001

Data Index: 1361335 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1383106 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.8974. Min Act: -0.0001

Data Index: 1392655 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 1.2170. Min Range: -1.2170

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1389037 (Python Code)

Max Activating Token Index: 19