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

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

Neuron 4059 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.8850. Min Act: -0.0000

Data Index: 1481374 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1492917 (Python Code)

Max Activating Token Index: 806

Text #2

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7824. Min Act: -0.0000

Data Index: 1609534 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1550625 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1507321 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7273. Min Act: -0.0000

Data Index: 1414291 (Python Code)

Max Activating Token Index: 855

Text #6

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1468783 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7593. Min Act: -0.0000

Data Index: 1528447 (Python Code)

Max Activating Token Index: 950

Text #8

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1370248 (Python Code)

Max Activating Token Index: 744

Text #9

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1360480 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.6063. Min Act: -0.0000

Data Index: 1395511 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1474808 (Python Code)

Max Activating Token Index: 956

Text #12

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5097. Min Act: -0.0000

Data Index: 1444319 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1555917 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1420949 (Python Code)

Max Activating Token Index: 951

Text #15

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5152. Min Act: -0.0000

Data Index: 1587418 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1444335 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1479311 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1428640 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 1.8850. Min Range: -1.8850

Max Act: 1.5029. Min Act: -0.0000

Data Index: 1584220 (Python Code)

Max Activating Token Index: 930