Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 279 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3314. Min Act: -0.0001

Data Index: 593218 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3132. Min Act: -0.0001

Data Index: 429297 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1134729 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2767. Min Act: -0.0001

Data Index: 360925 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2909. Min Act: -0.0001

Data Index: 763897 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2890. Min Act: -0.0001

Data Index: 835628 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2848. Min Act: -0.0001

Data Index: 609514 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2843. Min Act: -0.0001

Data Index: 159528 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2727. Min Act: -0.0001

Data Index: 418698 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2718. Min Act: -0.0001

Data Index: 407002 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2769. Min Act: -0.0001

Data Index: 957149 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1311247 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1114838 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2688. Min Act: -0.0001

Data Index: 627687 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2878. Min Act: -0.0001

Data Index: 701550 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1050826 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2749. Min Act: -0.0001

Data Index: 700898 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2632. Min Act: -0.0001

Data Index: 62316 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.3314. Min Range: -0.3314

Max Act: 0.2630. Min Act: -0.0001

Data Index: 387390 (C4 (Web Text))

Max Activating Token Index: 860