Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2189 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1470274 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1560312 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1641747 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1586256 (Python Code)

Max Activating Token Index: 33

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1418258 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1417618 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1595410 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1501488 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1638534 (Python Code)

Max Activating Token Index: 41

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1368038 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1539128 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1532146 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1474064 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1609676 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1643689 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1581251 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1628371 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1522676 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1576862 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1498789 (Python Code)

Max Activating Token Index: 17