Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0002

Data Index: 731577 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1582578 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1043445 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1541212 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1447464 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0609. Min Act: -0.0003

Data Index: 52793 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1412845 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0611. Min Act: -0.0003

Data Index: 1055832 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0582. Min Act: -0.0004

Data Index: 170465 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0592. Min Act: -0.0002

Data Index: 208909 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1467250 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1504620 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1471562 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1363493 (Python Code)

Max Activating Token Index: 697

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1574139 (Python Code)

Max Activating Token Index: 520

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1170022 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1612446 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1590370 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1618309 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1422099 (Python Code)

Max Activating Token Index: 466