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

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

Neuron 3522 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: 0.1641. Min Range: -0.1641

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1621583 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1599748 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1413918 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1498421 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1564516 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1590913 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1609669 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1470909 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1490762 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1593028 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1462503 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1424158 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1379869 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1442148 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1477838 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1631244 (Python Code)

Max Activating Token Index: 58

Text #16

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1383042 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1649491 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1442098 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 0.1641. Min Range: -0.1641

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1619660 (Python Code)

Max Activating Token Index: 24