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

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

Neuron 3003 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: 3.5762. Min Range: -3.5762

Max Act: 3.5762. Min Act: -0.0001

Data Index: 1423895 (Python Code)

Max Activating Token Index: 241

Text #1

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.3329. Min Act: -0.0001

Data Index: 1392961 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.2694. Min Act: -0.0001

Data Index: 1402030 (Python Code)

Max Activating Token Index: 922

Text #3

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.9698. Min Act: -0.0001

Data Index: 1469816 (Python Code)

Max Activating Token Index: 780

Text #4

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.2225. Min Act: -0.0001

Data Index: 1365780 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.1862. Min Act: -0.0000

Data Index: 1526585 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.3101. Min Act: -0.0000

Data Index: 1450793 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.8655. Min Act: -0.0001

Data Index: 1502486 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.1418. Min Act: -0.0001

Data Index: 1580671 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.1401. Min Act: -0.0001

Data Index: 1447757 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1409900 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.9824. Min Act: -0.0001

Data Index: 1377143 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.5741. Min Act: -0.0001

Data Index: 1511515 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.8600. Min Act: -0.0001

Data Index: 1521198 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.0021. Min Act: -0.0001

Data Index: 1646833 (Python Code)

Max Activating Token Index: 834

Text #15

Max Range: 3.5762. Min Range: -3.5762

Max Act: 3.2509. Min Act: -0.0001

Data Index: 1371710 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.9936. Min Act: -0.0000

Data Index: 1559555 (Python Code)

Max Activating Token Index: 861

Text #17

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.8262. Min Act: -0.0001

Data Index: 1519313 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.9538. Min Act: -0.0001

Data Index: 1599366 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 3.5762. Min Range: -3.5762

Max Act: 2.9447. Min Act: -0.0000

Data Index: 1554821 (Python Code)

Max Activating Token Index: 410