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

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

Neuron 2995 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: 2.9580. Min Range: -2.9580

Max Act: 2.9580. Min Act: -0.0000

Data Index: 1602163 (Python Code)

Max Activating Token Index: 509

Text #1

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1546573 (Python Code)

Max Activating Token Index: 605

Text #2

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.7290. Min Act: -0.0000

Data Index: 1590300 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.5019. Min Act: -0.0000

Data Index: 1528501 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.5928. Min Act: -0.0000

Data Index: 1629724 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.2982. Min Act: -0.0000

Data Index: 1479966 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.4225. Min Act: -0.0000

Data Index: 1621015 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.2468. Min Act: -0.0000

Data Index: 1529434 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.2581. Min Act: -0.0000

Data Index: 1644993 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.0265. Min Act: -0.0000

Data Index: 1445589 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.1491. Min Act: -0.0000

Data Index: 1372663 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.1504. Min Act: -0.0000

Data Index: 1439435 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.0796. Min Act: -0.0000

Data Index: 1614032 (Python Code)

Max Activating Token Index: 812

Text #13

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1623168 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.1655. Min Act: -0.0000

Data Index: 1648731 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.9842. Min Act: -0.0000

Data Index: 1597704 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1432782 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1378206 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.8736. Min Act: 0.0000

Data Index: 1501862 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.9444. Min Act: -0.0000

Data Index: 588801 (C4 (Web Text))

Max Activating Token Index: 315