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

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

Neuron 1034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1614603 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1540944 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1570436 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1491429 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1626616 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1459256 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1581708 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1525850 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1407701 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1366698 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1415009 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1487795 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1407536 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1394914 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1383576 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1375892 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1383944 (Python Code)

Max Activating Token Index: 122

Text #17

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1564372 (Python Code)

Max Activating Token Index: 60

Text #18

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1656804 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1527020 (Python Code)

Max Activating Token Index: 188