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

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

Neuron 1304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1553942 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0718. Min Act: -0.0001

Data Index: 1630993 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1519744 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1456969 (Python Code)

Max Activating Token Index: 506

Text #4

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1652851 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0647. Min Act: -0.0000

Data Index: 900514 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1581519 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9406. Min Act: -0.0000

Data Index: 735521 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1462331 (Python Code)

Max Activating Token Index: 656

Text #9

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1457548 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1574158 (Python Code)

Max Activating Token Index: 412

Text #11

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1393877 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1551223 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9437. Min Act: -0.0000

Data Index: 972851 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9673. Min Act: -0.0000

Data Index: 551553 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1489126 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1586828 (Python Code)

Max Activating Token Index: 763

Text #17

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1422449 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1216305 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1554685 (Python Code)

Max Activating Token Index: 536