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

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

Neuron 234 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.9062. Min Act: -0.0000

Data Index: 1544493 (Python Code)

Max Activating Token Index: 632

Text #1

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.7116. Min Act: -0.0000

Data Index: 1574373 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.2981. Min Act: -0.0000

Data Index: 1537722 (Python Code)

Max Activating Token Index: 575

Text #3

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.0460. Min Act: -0.0000

Data Index: 1571536 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.0251. Min Act: -0.0000

Data Index: 1653090 (Python Code)

Max Activating Token Index: 460

Text #5

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8986. Min Act: -0.0000

Data Index: 1405475 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8603. Min Act: -0.0000

Data Index: 1646649 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.1205. Min Act: -0.0000

Data Index: 1377538 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1451616 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8760. Min Act: -0.0000

Data Index: 1372748 (Python Code)

Max Activating Token Index: 513

Text #10

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8258. Min Act: -0.0000

Data Index: 1541560 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 3.9062. Min Range: -3.9062

Max Act: 3.0999. Min Act: -0.0000

Data Index: 1577997 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.6867. Min Act: -0.0001

Data Index: 1370334 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.8062. Min Act: -0.0000

Data Index: 1483340 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.7932. Min Act: -0.0000

Data Index: 1417100 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.9221. Min Act: -0.0000

Data Index: 1526959 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.9073. Min Act: -0.0000

Data Index: 1501998 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.7640. Min Act: -0.0000

Data Index: 1417503 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.7544. Min Act: -0.0000

Data Index: 1366260 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 3.9062. Min Range: -3.9062

Max Act: 2.6047. Min Act: -0.0000

Data Index: 1372513 (Python Code)

Max Activating Token Index: 365