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

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

Neuron 4756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1438818 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1636861 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1507554 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1360240 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1369457 (Python Code)

Max Activating Token Index: 488

Text #5

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1544488 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1364405 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1490792 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1631700 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1393036 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1449820 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1479266 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1516254 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1402961 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1390632 (Python Code)

Max Activating Token Index: 316

Text #15

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1445817 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1592124 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1440239 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1578152 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1540016 (Python Code)

Max Activating Token Index: 31