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

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

Neuron 1556 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: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1609411 (Python Code)

Max Activating Token Index: 58

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1645221 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1515354 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1603507 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1443234 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1560585 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1365864 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1635185 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1498029 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1360120 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1540892 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1567904 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1376943 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1655203 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1630238 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1370339 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1361210 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1557287 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1488004 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1544143 (Python Code)

Max Activating Token Index: 26