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

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

Neuron 1857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.4285. Min Act: -0.0000

Data Index: 1642722 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1653926 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1727. Min Act: 0.0001

Data Index: 1421702 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0365. Min Act: 0.0001

Data Index: 1609192 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0814. Min Act: 0.0001

Data Index: 1583901 (Python Code)

Max Activating Token Index: 43

Text #5

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1421863 (Python Code)

Max Activating Token Index: 692

Text #6

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1567419 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9780. Min Act: 0.0001

Data Index: 1461672 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0285. Min Act: 0.0000

Data Index: 1431972 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9933. Min Act: 0.0001

Data Index: 1441261 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1636079 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1411884 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0478. Min Act: 0.0001

Data Index: 1427983 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1545615 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1521390 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.4285. Min Range: -1.4285

Max Act: 1.0032. Min Act: 0.0001

Data Index: 1600043 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1360171 (Python Code)

Max Activating Token Index: 446

Text #17

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9402. Min Act: 0.0000

Data Index: 1474619 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1447129 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 1.4285. Min Range: -1.4285

Max Act: 0.9367. Min Act: 0.0001

Data Index: 1417834 (Python Code)

Max Activating Token Index: 180