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

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

Neuron 1450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.7458. Min Act: -0.0000

Data Index: 14222 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1005894 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6324. Min Act: -0.0000

Data Index: 21230 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6362. Min Act: -0.0000

Data Index: 71714 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1349550 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5889. Min Act: -0.0000

Data Index: 768218 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1142541 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1037102 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1163778 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6263. Min Act: -0.0000

Data Index: 458046 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1202692 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5938. Min Act: -0.0000

Data Index: 586092 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5672. Min Act: -0.0000

Data Index: 221090 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5772. Min Act: -0.0000

Data Index: 358927 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1016228 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5822. Min Act: -0.0000

Data Index: 576915 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5887. Min Act: -0.0000

Data Index: 352029 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5709. Min Act: -0.0000

Data Index: 779574 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5727. Min Act: -0.0000

Data Index: 600291 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.7458. Min Range: -0.7458

Max Act: 0.5442. Min Act: -0.0000

Data Index: 776447 (C4 (Web Text))

Max Activating Token Index: 277