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

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

Neuron 1595 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6600. Min Range: -2.6600

Max Act: 2.6600. Min Act: -0.0000

Data Index: 1368929 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 2.6600. Min Range: -2.6600

Max Act: 2.3073. Min Act: -0.0000

Data Index: 1594954 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.8378. Min Act: -0.0000

Data Index: 1391369 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 2.6600. Min Range: -2.6600

Max Act: 2.0050. Min Act: -0.0000

Data Index: 1456891 (Python Code)

Max Activating Token Index: 775

Text #4

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1474009 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.8392. Min Act: -0.0000

Data Index: 1514072 (Python Code)

Max Activating Token Index: 836

Text #6

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1584108 (Python Code)

Max Activating Token Index: 804

Text #7

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7656. Min Act: -0.0000

Data Index: 1590870 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1365165 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1417993 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1444915 (Python Code)

Max Activating Token Index: 165

Text #11

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7381. Min Act: -0.0000

Data Index: 1446614 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1589128 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1402778 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1435238 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1606628 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7413. Min Act: -0.0000

Data Index: 1552722 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1617393 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1622519 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 2.6600. Min Range: -2.6600

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1449100 (Python Code)

Max Activating Token Index: 583