Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1477590 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1485784 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1602367 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1496734 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1591632 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1503180 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1529546 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1589605 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1494715 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1591784 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2003. Min Act: -0.0000

Data Index: 234998 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1421676 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1645805 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1490750 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1461679 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1571661 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1629372 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1365962 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1521846 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 0.2552. Min Range: -0.2552

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1590640 (Python Code)

Max Activating Token Index: 900