Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3175 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9752. Min Act: -0.0001

Data Index: 1594845 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7970. Min Act: -0.0001

Data Index: 1490616 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1628176 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7904. Min Act: -0.0000

Data Index: 824505 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1639592 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1576600 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5503. Min Act: -0.0001

Data Index: 1451947 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1404575 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1149230 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1360220 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5304. Min Act: -0.0000

Data Index: 597747 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5006. Min Act: -0.0000

Data Index: 844301 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4952. Min Act: -0.0000

Data Index: 240283 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1403890 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5290. Min Act: -0.0001

Data Index: 154241 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1166274 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5393. Min Act: -0.0001

Data Index: 940100 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1511057 (Python Code)

Max Activating Token Index: 967

Text #18

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.5285. Min Act: -0.0001

Data Index: 1573016 (Python Code)

Max Activating Token Index: 439

Text #19

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.4615. Min Act: -0.0000

Data Index: 115163 (C4 (Web Text))

Max Activating Token Index: 861