Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1805 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0006

Data Index: 743640 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0653. Min Act: -0.0006

Data Index: 364048 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0704. Min Act: -0.0006

Data Index: 475764 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0723. Min Act: -0.0006

Data Index: 393588 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0695. Min Act: -0.0006

Data Index: 69632 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0690. Min Act: -0.0006

Data Index: 30221 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0676. Min Act: -0.0006

Data Index: 227573 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0730. Min Act: -0.0006

Data Index: 501839 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0657. Min Act: -0.0006

Data Index: 306584 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0627. Min Act: -0.0006

Data Index: 499661 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0742. Min Act: -0.0006

Data Index: 813584 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0620. Min Act: -0.0006

Data Index: 802972 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0660. Min Act: -0.0006

Data Index: 930527 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0643. Min Act: -0.0006

Data Index: 1036041 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0708. Min Act: -0.0006

Data Index: 282412 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0687. Min Act: -0.0006

Data Index: 188889 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0650. Min Act: -0.0006

Data Index: 381734 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0610. Min Act: -0.0006

Data Index: 1041888 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0646. Min Act: -0.0006

Data Index: 669807 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0632. Min Act: -0.0006

Data Index: 816696 (C4 (Web Text))

Max Activating Token Index: 728