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

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

Neuron 4920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1650552 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1615525 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1124. Min Act: -0.0002

Data Index: 1639494 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1431275 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1511246 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1436580 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1445357 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1512173 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1528076 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1570419 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1549972 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1529424 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1510844 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1416049 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1463772 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1434580 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1583466 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1597559 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1562572 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1630428 (Python Code)

Max Activating Token Index: 4