Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1645796 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1557669 (Python Code)

Max Activating Token Index: 842

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1374513 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1465513 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1447660 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1614837 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1411474 (Python Code)

Max Activating Token Index: 969

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1509404 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1440691 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1376954 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1473162 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1373283 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1502433 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1601068 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1525295 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1416467 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1622458 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1405470 (Python Code)

Max Activating Token Index: 697

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1473787 (Python Code)

Max Activating Token Index: 870

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1481286 (Python Code)

Max Activating Token Index: 965