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

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

Neuron 1903 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: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1413229 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1389681 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1533059 (Python Code)

Max Activating Token Index: 937

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1057. Min Act: -0.0002

Data Index: 661252 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1065. Min Act: -0.0002

Data Index: 215763 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1455637 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1408174 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1597899 (Python Code)

Max Activating Token Index: 942

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1075. Min Act: -0.0002

Data Index: 63421 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1410112 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0978. Min Act: -0.0002

Data Index: 605218 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1654390 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1007906 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1155404 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1002. Min Act: -0.0002

Data Index: 549669 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0961. Min Act: -0.0002

Data Index: 329895 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1462415 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1447972 (Python Code)

Max Activating Token Index: 873

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0990. Min Act: -0.0002

Data Index: 533019 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0974. Min Act: -0.0002

Data Index: 404564 (C4 (Web Text))

Max Activating Token Index: 368