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

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

Neuron 3201 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5424. Min Range: -6.5424

Max Act: 6.5424. Min Act: -0.0000

Data Index: 1650300 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.9864. Min Act: -0.0000

Data Index: 1368267 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.8259. Min Act: -0.0000

Data Index: 1432688 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.6509. Min Act: -0.0000

Data Index: 1401950 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.6409. Min Act: -0.0000

Data Index: 1421041 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 6.5424. Min Range: -6.5424

Max Act: 6.1820. Min Act: -0.0000

Data Index: 1403725 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.8006. Min Act: -0.0000

Data Index: 1474349 (Python Code)

Max Activating Token Index: 942

Text #7

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.3251. Min Act: -0.0000

Data Index: 1630619 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.3328. Min Act: -0.0000

Data Index: 1511941 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.4905. Min Act: -0.0000

Data Index: 1497259 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.8167. Min Act: -0.0000

Data Index: 1484392 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.8129. Min Act: -0.0000

Data Index: 1608786 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.6176. Min Act: -0.0000

Data Index: 1467229 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.7932. Min Act: -0.0000

Data Index: 1497729 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.5827. Min Act: -0.0000

Data Index: 1434208 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.5244. Min Act: -0.0000

Data Index: 1475346 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.4977. Min Act: -0.0000

Data Index: 1596816 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.3299. Min Act: -0.0000

Data Index: 1515925 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.6510. Min Act: -0.0000

Data Index: 1450163 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 6.5424. Min Range: -6.5424

Max Act: 5.5305. Min Act: -0.0000

Data Index: 1392890 (Python Code)

Max Activating Token Index: 377