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

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

Neuron 1955 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8784. Min Act: 0.0000

Data Index: 1435166 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1492750 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8311. Min Act: 0.0000

Data Index: 1469870 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7703. Min Act: 0.0000

Data Index: 1646001 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1514001 (Python Code)

Max Activating Token Index: 657

Text #5

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1464120 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6667. Min Act: 0.0000

Data Index: 1598559 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1592304 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1392307 (Python Code)

Max Activating Token Index: 696

Text #9

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1577601 (Python Code)

Max Activating Token Index: 796

Text #10

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1472988 (Python Code)

Max Activating Token Index: 757

Text #11

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1596361 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1618688 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5709. Min Act: 0.0000

Data Index: 1521760 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5891. Min Act: 0.0000

Data Index: 1386855 (Python Code)

Max Activating Token Index: 558

Text #15

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5872. Min Act: 0.0000

Data Index: 1422519 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1474825 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1582149 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1422457 (Python Code)

Max Activating Token Index: 687

Text #19

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5562. Min Act: 0.0000

Data Index: 1646311 (Python Code)

Max Activating Token Index: 972