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

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

Neuron 4636 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: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0002

Data Index: 316950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0003

Data Index: 494488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0055. Min Act: -0.0002

Data Index: 785819 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1137862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0056. Min Act: -0.0002

Data Index: 923724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0003

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0053. Min Act: -0.0002

Data Index: 744410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1584895 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1320841 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0049. Min Act: -0.0002

Data Index: 902324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0045. Min Act: -0.0002

Data Index: 948665 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1254647 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0048. Min Act: -0.0003

Data Index: 499786 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0046. Min Act: -0.0003

Data Index: 927919 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0045. Min Act: -0.0002

Data Index: 993879 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0045. Min Act: -0.0003

Data Index: 873572 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0045. Min Act: -0.0003

Data Index: 35195 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1509800 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 768113 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0044. Min Act: -0.0003

Data Index: 159295 (C4 (Web Text))

Max Activating Token Index: 16