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

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

Neuron 1066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1524610 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1465551 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1371002 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1613600 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1381373 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1635962 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1503580 (Python Code)

Max Activating Token Index: 387

Text #7

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8651. Min Act: -0.0000

Data Index: 1403538 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1551517 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1477058 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1533664 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.8926. Min Act: -0.0000

Data Index: 1593966 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1405339 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1438382 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1430471 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1540547 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1546505 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1634018 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1538899 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 0.9356. Min Range: -0.9356

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1444156 (Python Code)

Max Activating Token Index: 823