Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2682 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1287661 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 39860 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 912468 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1547805 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1030291 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 773675 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 452016 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1247393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1048848 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 959564 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1150429 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1099493 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 777984 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 653649 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 992546 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 98968 (C4 (Web Text))

Max Activating Token Index: 111