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

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

Neuron 2566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1075052 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1510281 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0767. Min Act: -0.0000

Data Index: 692678 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1624310 (Python Code)

Max Activating Token Index: 848

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0695. Min Act: -0.0000

Data Index: 269813 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1497514 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1432857 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1575092 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1456215 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0626. Min Act: -0.0000

Data Index: 708247 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1389729 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1570322 (Python Code)

Max Activating Token Index: 962

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1492019 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1570493 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1171613 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1479553 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0688. Min Act: -0.0000

Data Index: 726269 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1387500 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1636757 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1418286 (Python Code)

Max Activating Token Index: 547