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

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

Neuron 23 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1449897 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 1.0875. Min Range: -1.0875

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1589571 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1363487 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1643052 (Python Code)

Max Activating Token Index: 838

Text #4

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1506961 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1614924 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1530459 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1630316 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1615497 (Python Code)

Max Activating Token Index: 436

Text #9

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1375390 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1477647 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1600495 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1483072 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1626622 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1586178 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1546557 (Python Code)

Max Activating Token Index: 296

Text #16

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1367572 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1485867 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1532499 (Python Code)

Max Activating Token Index: 958

Text #19

Max Range: 1.0875. Min Range: -1.0875

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1460063 (Python Code)

Max Activating Token Index: 422