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

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

Neuron 2650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1624444 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1486360 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1408521 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1588748 (Python Code)

Max Activating Token Index: 30

Text #4

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1567561 (Python Code)

Max Activating Token Index: 884

Text #5

Max Range: 1.3239. Min Range: -1.3239

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1577273 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1386358 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1594131 (Python Code)

Max Activating Token Index: 362

Text #8

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1464561 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1434999 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9212. Min Act: -0.0001

Data Index: 1638486 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1476422 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1418328 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8868. Min Act: -0.0000

Data Index: 1607724 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1507110 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1592991 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1548643 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1536593 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1549716 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 1.3239. Min Range: -1.3239

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1542874 (Python Code)

Max Activating Token Index: 430