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

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

Neuron 5526 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: 2.7052. Min Range: -2.7052

Max Act: 2.6825. Min Act: -0.0000

Data Index: 1497703 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1647029 (Python Code)

Max Activating Token Index: 746

Text #2

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.6080. Min Act: -0.0000

Data Index: 1415477 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.7052. Min Act: -0.0000

Data Index: 1652785 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.4261. Min Act: -0.0000

Data Index: 1566453 (Python Code)

Max Activating Token Index: 560

Text #5

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.2149. Min Act: -0.0000

Data Index: 1641160 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1989. Min Act: -0.0000

Data Index: 1539091 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.3023. Min Act: -0.0000

Data Index: 1361274 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1874. Min Act: -0.0000

Data Index: 1367391 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1737. Min Act: -0.0000

Data Index: 1400666 (Python Code)

Max Activating Token Index: 608

Text #10

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1721. Min Act: -0.0000

Data Index: 1643798 (Python Code)

Max Activating Token Index: 705

Text #11

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.0668. Min Act: -0.0000

Data Index: 1600716 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1505224 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1370062 (Python Code)

Max Activating Token Index: 836

Text #14

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.0569. Min Act: -0.0000

Data Index: 1558520 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.0556. Min Act: -0.0000

Data Index: 1381515 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1534. Min Act: -0.0000

Data Index: 1592656 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1700. Min Act: -0.0000

Data Index: 1486785 (Python Code)

Max Activating Token Index: 555

Text #18

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1351. Min Act: -0.0000

Data Index: 1401001 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 2.7052. Min Range: -2.7052

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1405378 (Python Code)

Max Activating Token Index: 711