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

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

Neuron 2858 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.2000. Min Act: -0.0002

Data Index: 1390821 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1994. Min Act: -0.0002

Data Index: 1453528 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1507557 (Python Code)

Max Activating Token Index: 63

Text #3

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1950. Min Act: -0.0002

Data Index: 1550266 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1485992 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1917. Min Act: -0.0002

Data Index: 1591081 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1947. Min Act: -0.0002

Data Index: 1459191 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1910. Min Act: -0.0002

Data Index: 1400145 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1933. Min Act: -0.0002

Data Index: 1406453 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1433543 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1892. Min Act: -0.0002

Data Index: 1626220 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1929. Min Act: -0.0002

Data Index: 1413044 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1854. Min Act: -0.0002

Data Index: 1563662 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1913. Min Act: -0.0002

Data Index: 1448596 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1601939 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1858. Min Act: -0.0002

Data Index: 1599794 (Python Code)

Max Activating Token Index: 708

Text #16

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1442954 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1452600 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1440490 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1834. Min Act: -0.0002

Data Index: 1585099 (Python Code)

Max Activating Token Index: 981