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

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

Neuron 4350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0268. Min Range: -1.0268

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1516581 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1540269 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1408171 (Python Code)

Max Activating Token Index: 722

Text #3

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1486505 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1379350 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1404264 (Python Code)

Max Activating Token Index: 513

Text #6

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1570179 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7222. Min Act: -0.0000

Data Index: 1640520 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1599264 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1608774 (Python Code)

Max Activating Token Index: 131

Text #10

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1476552 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1596901 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1647877 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1574446 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1652445 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1642404 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1593125 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1590191 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1545623 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1631390 (Python Code)

Max Activating Token Index: 43