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

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

Neuron 2798 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.5584. Min Act: -0.0000

Data Index: 1597539 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.4883. Min Act: -0.0000

Data Index: 1628032 (Python Code)

Max Activating Token Index: 893

Text #2

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.3991. Min Act: -0.0000

Data Index: 1529025 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.2643. Min Act: -0.0000

Data Index: 1564950 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1501. Min Act: -0.0000

Data Index: 1597999 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1626667 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1641. Min Act: -0.0000

Data Index: 1426461 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.9123. Min Act: -0.0000

Data Index: 1415330 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1464465 (Python Code)

Max Activating Token Index: 47

Text #9

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1037. Min Act: -0.0000

Data Index: 1650542 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.0756. Min Act: -0.0000

Data Index: 1498421 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1490. Min Act: -0.0000

Data Index: 1442182 (Python Code)

Max Activating Token Index: 929

Text #12

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1574. Min Act: -0.0000

Data Index: 1437129 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1420355 (Python Code)

Max Activating Token Index: 709

Text #14

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.1378. Min Act: -0.0000

Data Index: 1489984 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 2.5584. Min Range: -2.5584

Max Act: 2.0164. Min Act: -0.0000

Data Index: 1520606 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1387398 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.9707. Min Act: -0.0000

Data Index: 1388265 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.9503. Min Act: -0.0000

Data Index: 1513831 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 2.5584. Min Range: -2.5584

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1522293 (Python Code)

Max Activating Token Index: 45