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

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

Neuron 3494 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1464235 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1407151 (Python Code)

Max Activating Token Index: 724

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1424331 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1568655 (Python Code)

Max Activating Token Index: 879

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1516503 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1112. Min Act: -0.0002

Data Index: 120459 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1496751 (Python Code)

Max Activating Token Index: 765

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1569791 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1040. Min Act: -0.0002

Data Index: 63400 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1003739 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1067. Min Act: -0.0002

Data Index: 459112 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1074326 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1539263 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1074. Min Act: -0.0002

Data Index: 219283 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1606017 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1502922 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0921. Min Act: -0.0002

Data Index: 961038 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1040. Min Act: -0.0002

Data Index: 372067 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0986. Min Act: -0.0002

Data Index: 116926 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1477014 (Python Code)

Max Activating Token Index: 974