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

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

Neuron 6006 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1619923 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3465. Min Act: -0.0001

Data Index: 1360893 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1503195 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1446971 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1468319 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3226. Min Act: -0.0001

Data Index: 1656033 (Python Code)

Max Activating Token Index: 74

Text #6

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1413623 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1622235 (Python Code)

Max Activating Token Index: 115

Text #8

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1468590 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3062. Min Act: -0.0001

Data Index: 1506076 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3081. Min Act: -0.0001

Data Index: 1542848 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1613132 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3004. Min Act: -0.0001

Data Index: 1492168 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3023. Min Act: -0.0002

Data Index: 1412791 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1559555 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2943. Min Act: -0.0001

Data Index: 1461349 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1404938 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1437995 (Python Code)

Max Activating Token Index: 936

Text #18

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1366756 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1627405 (Python Code)

Max Activating Token Index: 40