Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1318 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1116. Min Act: -0.0003

Data Index: 606157 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0997. Min Act: -0.0003

Data Index: 1437782 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1032. Min Act: -0.0003

Data Index: 1577844 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1001. Min Act: -0.0003

Data Index: 1429660 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0955. Min Act: -0.0003

Data Index: 345078 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1418054 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0962. Min Act: -0.0003

Data Index: 964517 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1039. Min Act: -0.0003

Data Index: 189149 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0982. Min Act: -0.0003

Data Index: 1498737 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1362529 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1623605 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0846. Min Act: -0.0003

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0900. Min Act: -0.0003

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0830. Min Act: -0.0003

Data Index: 281307 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0879. Min Act: -0.0003

Data Index: 1393634 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1372268 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 0.1116. Min Range: -0.1116

Max Act: 0.0849. Min Act: -0.0003

Data Index: 1566237 (Python Code)

Max Activating Token Index: 780