Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 973 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0005

Data Index: 1479310 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1528014 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0006

Data Index: 176670 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0006

Data Index: 199005 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1548549 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0055. Min Act: -0.0006

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0054. Min Act: -0.0006

Data Index: 181356 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1444275 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0006

Data Index: 830225 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1161155 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1483353 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1600569 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1387286 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0006

Data Index: 875124 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0006

Data Index: 455466 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0006

Data Index: 670269 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1473880 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0006

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0005

Data Index: 1471271 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0006

Data Index: 858072 (C4 (Web Text))

Max Activating Token Index: 631