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

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

Neuron 590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.4159. Min Act: -0.0000

Data Index: 542245 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3975. Min Act: -0.0000

Data Index: 70065 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3750. Min Act: -0.0000

Data Index: 222135 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3354. Min Act: -0.0000

Data Index: 439023 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3062. Min Act: -0.0000

Data Index: 241601 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1063734 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2995. Min Act: -0.0000

Data Index: 328891 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3045. Min Act: -0.0000

Data Index: 54313 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2868. Min Act: -0.0000

Data Index: 630785 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1247345 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.3031. Min Act: -0.0000

Data Index: 830765 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2920. Min Act: -0.0000

Data Index: 713590 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2731. Min Act: -0.0000

Data Index: 954641 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2807. Min Act: -0.0000

Data Index: 864660 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2798. Min Act: -0.0000

Data Index: 179884 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1079537 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2502. Min Act: -0.0000

Data Index: 443113 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2603. Min Act: -0.0000

Data Index: 955723 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2652. Min Act: -0.0001

Data Index: 1187348 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.4159. Min Range: -0.4159

Max Act: 0.2531. Min Act: -0.0000

Data Index: 904812 (C4 (Web Text))

Max Activating Token Index: 71