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

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

Neuron 3408 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: 0.1125. Min Range: -0.1125

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1542945 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1550100 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1608547 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1451893 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1585079 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1426435 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1379227 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1034. Min Act: -0.0001

Data Index: 760132 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1381384 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1381023 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1431736 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1493678 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1549238 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1524219 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1605129 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1565394 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1630217 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1574356 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1406992 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1642397 (Python Code)

Max Activating Token Index: 1023