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

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

Neuron 1724 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.7710. Min Act: -0.0001

Data Index: 1362218 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.5706. Min Act: -0.0001

Data Index: 1499660 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.2627. Min Act: -0.0001

Data Index: 1423854 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1952. Min Act: -0.0001

Data Index: 1395365 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.5958. Min Act: -0.0001

Data Index: 1597639 (Python Code)

Max Activating Token Index: 656

Text #5

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.2738. Min Act: -0.0001

Data Index: 1625453 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.3488. Min Act: -0.0001

Data Index: 1524146 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.2069. Min Act: -0.0001

Data Index: 1359946 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.3269. Min Act: -0.0001

Data Index: 1515178 (Python Code)

Max Activating Token Index: 641

Text #9

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1838. Min Act: -0.0001

Data Index: 1593214 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.3390. Min Act: -0.0001

Data Index: 1568265 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.2803. Min Act: -0.0001

Data Index: 1529360 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.4002. Min Act: -0.0001

Data Index: 1548276 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1350. Min Act: -0.0001

Data Index: 1564148 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.3951. Min Act: -0.0001

Data Index: 1519495 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.2212. Min Act: -0.0001

Data Index: 1413162 (Python Code)

Max Activating Token Index: 446

Text #16

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1647. Min Act: -0.0001

Data Index: 1450610 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1475. Min Act: -0.0001

Data Index: 1515192 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.1083. Min Act: -0.0001

Data Index: 1479304 (Python Code)

Max Activating Token Index: 641

Text #19

Max Range: 3.7710. Min Range: -3.7710

Max Act: 3.0927. Min Act: -0.0001

Data Index: 1561139 (Python Code)

Max Activating Token Index: 678