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

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

Neuron 1626 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0003

Data Index: 940162 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1405642 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1280582 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1589420 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1491805 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1525156 (Python Code)

Max Activating Token Index: 834

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1558116 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1598414 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1545745 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1501175 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1491727 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1407882 (Python Code)

Max Activating Token Index: 1000

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0003

Data Index: 784220 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0056. Min Act: -0.0003

Data Index: 400778 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0053. Min Act: -0.0003

Data Index: 72430 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1465152 (Python Code)

Max Activating Token Index: 711

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1207965 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1069556 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1569167 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1282463 (C4 (Web Text))

Max Activating Token Index: 672