Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1933 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.5825. Min Act: -0.0001

Data Index: 1546411 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.0378. Min Act: -0.0001

Data Index: 1483583 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3143. Min Act: -0.0001

Data Index: 1420220 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.6491. Min Act: -0.0001

Data Index: 1569552 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.8020. Min Act: -0.0001

Data Index: 1494007 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.9025. Min Act: -0.0001

Data Index: 1394644 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.8438. Min Act: -0.0001

Data Index: 1538974 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.8860. Min Act: -0.0001

Data Index: 1428839 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.0403. Min Act: -0.0001

Data Index: 1595836 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.0387. Min Act: -0.0001

Data Index: 1483549 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.7712. Min Act: -0.0001

Data Index: 1421922 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.7679. Min Act: -0.0001

Data Index: 1441966 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.3696. Min Act: -0.0001

Data Index: 1512369 (Python Code)

Max Activating Token Index: 861

Text #13

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.4603. Min Act: -0.0001

Data Index: 1456825 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.7824. Min Act: -0.0001

Data Index: 1624989 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.7855. Min Act: -0.0001

Data Index: 1471767 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.6026. Min Act: -0.0001

Data Index: 1380508 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.6165. Min Act: -0.0001

Data Index: 1638381 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.7519. Min Act: -0.0001

Data Index: 1519748 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 5.5825. Min Range: -5.5825

Max Act: 4.5719. Min Act: -0.0001

Data Index: 1536276 (Python Code)

Max Activating Token Index: 75