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

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

Neuron 1957 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: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1243263 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0081. Min Act: -0.0003

Data Index: 568613 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0075. Min Act: -0.0003

Data Index: 56431 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0065. Min Act: -0.0003

Data Index: 797922 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0061. Min Act: -0.0003

Data Index: 708323 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0061. Min Act: -0.0003

Data Index: 529429 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1520148 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0056. Min Act: -0.0003

Data Index: 229472 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1074528 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1489143 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0053. Min Act: -0.0003

Data Index: 117827 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0050. Min Act: -0.0003

Data Index: 245093 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1592229 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0054. Min Act: -0.0003

Data Index: 810776 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0052. Min Act: -0.0003

Data Index: 49760 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0053. Min Act: -0.0003

Data Index: 145496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0053. Min Act: -0.0002

Data Index: 695845 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0051. Min Act: -0.0003

Data Index: 298802 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0048. Min Act: -0.0003

Data Index: 133049 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1581610 (Python Code)

Max Activating Token Index: 49