Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0827. Min Act: -0.0003

Data Index: 1578410 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0819. Min Act: -0.0003

Data Index: 1537155 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1571254 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1478079 (Python Code)

Max Activating Token Index: 571

Text #4

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1519338 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1472585 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1559636 (Python Code)

Max Activating Token Index: 491

Text #7

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1493331 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1628599 (Python Code)

Max Activating Token Index: 427

Text #9

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1630697 (Python Code)

Max Activating Token Index: 916

Text #10

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1519482 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1441631 (Python Code)

Max Activating Token Index: 332

Text #12

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1587561 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1490887 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1405327 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1515559 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1448401 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1495112 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1450984 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 0.0827. Min Range: -0.0827

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1427480 (Python Code)

Max Activating Token Index: 894