Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3697 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1357183 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1389516 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1627553 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1449714 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1605666 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1523479 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1461793 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1588384 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1399141 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1519872 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1394204 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1580730 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1555764 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1441071 (Python Code)

Max Activating Token Index: 452

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1551069 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1642031 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1450722 (Python Code)

Max Activating Token Index: 151

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1377322 (Python Code)

Max Activating Token Index: 55

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1622816 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1446632 (Python Code)

Max Activating Token Index: 106