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

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

Neuron 2309 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: 0.9630. Min Range: -0.9630

Max Act: 0.9630. Min Act: -0.0000

Data Index: 273226 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1483519 (Python Code)

Max Activating Token Index: 409

Text #2

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1226352 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1587658 (Python Code)

Max Activating Token Index: 774

Text #4

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1391642 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1541026 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1587492 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1492016 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1397075 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1506969 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1435506 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1591826 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1509517 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1459654 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1383044 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1533137 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1596195 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1417034 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1631462 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.9630. Min Range: -0.9630

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1583203 (Python Code)

Max Activating Token Index: 1018