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

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

Neuron 4175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0821. Min Act: -0.0002

Data Index: 694301 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1253473 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1119770 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1521625 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1427666 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1469400 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1495073 (Python Code)

Max Activating Token Index: 333

Text #7

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0729. Min Act: -0.0002

Data Index: 899656 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0710. Min Act: -0.0002

Data Index: 193449 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1522692 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0724. Min Act: -0.0002

Data Index: 766812 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0671. Min Act: -0.0002

Data Index: 761716 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0697. Min Act: -0.0002

Data Index: 31572 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1630333 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1639183 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1573126 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1595970 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0663. Min Act: -0.0002

Data Index: 99169 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1534189 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 0.0821. Min Range: -0.0821

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1564664 (Python Code)

Max Activating Token Index: 645