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

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

Neuron 3420 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1148839 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1009183 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1223955 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1820. Min Act: -0.0001

Data Index: 732180 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1912. Min Act: -0.0000

Data Index: 220020 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1048490 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1702. Min Act: -0.0000

Data Index: 162844 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1728. Min Act: -0.0000

Data Index: 295916 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1674. Min Act: -0.0000

Data Index: 180753 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1595. Min Act: -0.0000

Data Index: 717151 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1288308 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1125525 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1746. Min Act: -0.0000

Data Index: 466574 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1045272 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1585. Min Act: -0.0000

Data Index: 111675 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1619. Min Act: -0.0000

Data Index: 793909 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1480. Min Act: -0.0001

Data Index: 106960 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1640. Min Act: -0.0000

Data Index: 378230 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1311411 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2086. Min Range: -0.2086

Max Act: 0.1513. Min Act: -0.0000

Data Index: 760398 (C4 (Web Text))

Max Activating Token Index: 15