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

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

Neuron 160 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1457381 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1591503 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1487986 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1592661 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1443705 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1604381 (Python Code)

Max Activating Token Index: 32

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1584714 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1548425 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1540690 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1258823 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1589335 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1589696 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1576454 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1399057 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1363598 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1590809 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1535094 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1365710 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1397262 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1622241 (Python Code)

Max Activating Token Index: 398