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

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

Neuron 5123 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: 2.1219. Min Range: -2.1219

Max Act: 2.1219. Min Act: -0.0002

Data Index: 1370044 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.1219. Min Range: -2.1219

Max Act: 2.0146. Min Act: -0.0001

Data Index: 1514133 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.9691. Min Act: -0.0001

Data Index: 1375857 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.9121. Min Act: -0.0001

Data Index: 1406741 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.9058. Min Act: -0.0001

Data Index: 1532103 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8806. Min Act: -0.0001

Data Index: 1449401 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.9044. Min Act: -0.0002

Data Index: 1378440 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8883. Min Act: -0.0002

Data Index: 1405911 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8678. Min Act: -0.0001

Data Index: 1397874 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.9039. Min Act: -0.0001

Data Index: 1414309 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8780. Min Act: -0.0001

Data Index: 1533622 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8914. Min Act: -0.0002

Data Index: 1383046 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8649. Min Act: -0.0001

Data Index: 1437149 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8800. Min Act: -0.0001

Data Index: 1461949 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8905. Min Act: -0.0002

Data Index: 1503658 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8881. Min Act: -0.0002

Data Index: 1448035 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8635. Min Act: -0.0001

Data Index: 1605569 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8584. Min Act: -0.0001

Data Index: 1620753 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8469. Min Act: -0.0001

Data Index: 1581413 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 2.1219. Min Range: -2.1219

Max Act: 1.8474. Min Act: -0.0001

Data Index: 1379306 (Python Code)

Max Activating Token Index: 1023