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

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

Neuron 3141 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: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0003

Data Index: 898714 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1140593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0061. Min Act: -0.0002

Data Index: 821268 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1406029 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1442571 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1584614 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1471091 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0054. Min Act: -0.0002

Data Index: 26814 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1516078 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0050. Min Act: -0.0002

Data Index: 417561 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0050. Min Act: -0.0002

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1241544 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0049. Min Act: -0.0003

Data Index: 375023 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0049. Min Act: -0.0003

Data Index: 636379 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0048. Min Act: -0.0002

Data Index: 876245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0049. Min Act: -0.0002

Data Index: 223065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1358976 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0048. Min Act: -0.0002

Data Index: 356146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0048. Min Act: -0.0002

Data Index: 47841 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0049. Min Act: -0.0003

Data Index: 1042494 (C4 (Web Text))

Max Activating Token Index: 1023