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

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

Neuron 189 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0001

Data Index: 641610 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0715. Min Act: -0.0001

Data Index: 990772 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0832. Min Act: -0.0001

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0790. Min Act: -0.0001

Data Index: 521507 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1036192 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0751. Min Act: -0.0001

Data Index: 334420 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0743. Min Act: -0.0001

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0787. Min Act: -0.0001

Data Index: 369293 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0730. Min Act: -0.0001

Data Index: 839606 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1621628 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0687. Min Act: -0.0001

Data Index: 684345 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0686. Min Act: -0.0001

Data Index: 528287 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1199059 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0655. Min Act: -0.0001

Data Index: 293953 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0696. Min Act: -0.0001

Data Index: 590952 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1158565 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0733. Min Act: -0.0001

Data Index: 45750 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0719. Min Act: -0.0001

Data Index: 230006 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1345531 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0757. Min Act: -0.0001

Data Index: 455067 (C4 (Web Text))

Max Activating Token Index: 78