Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1456895 (Python Code)

Max Activating Token Index: 228

Text #1

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1470234 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1440438 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1487585 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1623769 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1398536 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1487232 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1527246 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1611087 (Python Code)

Max Activating Token Index: 407

Text #9

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1389007 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1540905 (Python Code)

Max Activating Token Index: 805

Text #11

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1430416 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1536804 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1632995 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1490718 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1419124 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1592075 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 1.6995. Min Range: -1.6995

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1621461 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1449661 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1364482 (Python Code)

Max Activating Token Index: 38