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

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

Neuron 891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1560176 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1485818 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1654295 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1495074 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1596613 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1589968 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1561675 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1622537 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1429806 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1590315 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1955. Min Act: -0.0000

Data Index: 354289 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1604735 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1399524 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1628890 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1405130 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1381070 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1406308 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1602819 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1489561 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1376598 (Python Code)

Max Activating Token Index: 5