Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1505066 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1589677 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1525742 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1367628 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1393729 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1383577 (Python Code)

Max Activating Token Index: 587

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1635749 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1635992 (Python Code)

Max Activating Token Index: 582

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1469260 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1485295 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1642636 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1464866 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1581578 (Python Code)

Max Activating Token Index: 704

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1394961 (Python Code)

Max Activating Token Index: 768

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1542065 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1489692 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1425634 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1384695 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1630883 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1432592 (Python Code)

Max Activating Token Index: 76