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

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

Neuron 752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1527677 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1495673 (Python Code)

Max Activating Token Index: 732

Text #2

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1546424 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1515959 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1528112 (Python Code)

Max Activating Token Index: 525

Text #5

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1391507 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1530879 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1486585 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1600677 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1603887 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1443964 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1627954 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1412666 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1391677 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1548408 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1511272 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1444800 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1611452 (Python Code)

Max Activating Token Index: 618

Text #18

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2003. Min Act: -0.0000

Data Index: 19339 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1491564 (Python Code)

Max Activating Token Index: 975