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

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

Neuron 1099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1404787 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1497548 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1545257 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1478895 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1584011 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1653672 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1369982 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1507702 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1655593 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1386345 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1378899 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1482357 (Python Code)

Max Activating Token Index: 849

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1448485 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1509904 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1605940 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1616643 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1598021 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1376312 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1384236 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1570442 (Python Code)

Max Activating Token Index: 255