Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.5992. Min Act: -0.0001

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4045. Min Act: -0.0001

Data Index: 1621307 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4062. Min Act: -0.0001

Data Index: 1507774 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1607927 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1421296 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.4016. Min Act: -0.0001

Data Index: 1602421 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3989. Min Act: -0.0001

Data Index: 1418401 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3829. Min Act: -0.0001

Data Index: 1640976 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3811. Min Act: -0.0001

Data Index: 1616512 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3938. Min Act: -0.0001

Data Index: 1537779 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1460426 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1536417 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1497902 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3910. Min Act: -0.0001

Data Index: 1423740 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1648190 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3904. Min Act: -0.0001

Data Index: 1545255 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1536816 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3896. Min Act: -0.0001

Data Index: 1503153 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3868. Min Act: -0.0001

Data Index: 1628492 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 0.5992. Min Range: -0.5992

Max Act: 0.3822. Min Act: -0.0001

Data Index: 1607320 (Python Code)

Max Activating Token Index: 34