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

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

Neuron 2028 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0002

Data Index: 516960 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0900. Min Act: -0.0002

Data Index: 847044 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1110598 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1200624 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1025743 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0809. Min Act: -0.0002

Data Index: 666702 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1164978 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0780. Min Act: -0.0002

Data Index: 430535 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0799. Min Act: -0.0002

Data Index: 872812 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1047573 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0746. Min Act: -0.0002

Data Index: 59962 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0739. Min Act: -0.0002

Data Index: 286976 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0740. Min Act: -0.0002

Data Index: 589336 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0748. Min Act: -0.0002

Data Index: 436037 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0727. Min Act: -0.0002

Data Index: 525044 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0709. Min Act: -0.0001

Data Index: 55222 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1134600 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1060257 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1099015 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1087941 (C4 (Web Text))

Max Activating Token Index: 390