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

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

Neuron 3563 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: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1616409 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0062. Min Act: -0.0003

Data Index: 656748 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1513799 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1392904 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1438864 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1371204 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1392905 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1595457 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1654853 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1442115 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1375156 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1361714 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1370086 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1636204 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1637712 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1519915 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1448400 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1645918 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0003

Data Index: 96425 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1473507 (Python Code)

Max Activating Token Index: 251