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

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

Neuron 3959 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0095. Min Range: -2.0095

Max Act: 2.0095. Min Act: -0.0000

Data Index: 1421687 (Python Code)

Max Activating Token Index: 473

Text #1

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.9538. Min Act: -0.0000

Data Index: 1411879 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.8348. Min Act: -0.0000

Data Index: 1525950 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.9069. Min Act: -0.0000

Data Index: 1505246 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1628553 (Python Code)

Max Activating Token Index: 438

Text #5

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1610483 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1516638 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1553896 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1517796 (Python Code)

Max Activating Token Index: 292

Text #9

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1568960 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1572889 (Python Code)

Max Activating Token Index: 898

Text #11

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.2645. Min Act: -0.0000

Data Index: 1458889 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1483561 (Python Code)

Max Activating Token Index: 642

Text #13

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1528821 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1453102 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1606639 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1506414 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1464464 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1618666 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1473105 (Python Code)

Max Activating Token Index: 110