Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1801. Min Act: -0.0002

Data Index: 1551800 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1448. Min Act: -0.0002

Data Index: 1624360 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1550795 (Python Code)

Max Activating Token Index: 242

Text #3

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1570665 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1639945 (Python Code)

Max Activating Token Index: 422

Text #5

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1444489 (Python Code)

Max Activating Token Index: 760

Text #6

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1415979 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1509658 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1561743 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1471138 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1521855 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1370947 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1487130 (Python Code)

Max Activating Token Index: 602

Text #13

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1506875 (Python Code)

Max Activating Token Index: 991

Text #14

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1488878 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1609520 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1611234 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1498226 (Python Code)

Max Activating Token Index: 609

Text #18

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1384843 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 0.1801. Min Range: -0.1801

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1411981 (Python Code)

Max Activating Token Index: 156