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

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

Neuron 3700 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: 0.1099. Min Range: -0.1099

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1386708 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1560887 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1582059 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1568537 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1473029 (Python Code)

Max Activating Token Index: 48

Text #5

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1023. Min Act: -0.0001

Data Index: 66000 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1438996 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1555208 (Python Code)

Max Activating Token Index: 252

Text #8

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1568369 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1405805 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1528472 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1588037 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1529429 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1517284 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1527750 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1398986 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1446642 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1637058 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1501351 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1649538 (Python Code)

Max Activating Token Index: 53