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

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

Neuron 3051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1001829 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6009. Min Act: -0.0000

Data Index: 74716 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5532. Min Act: -0.0000

Data Index: 703580 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5531. Min Act: -0.0000

Data Index: 776614 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5164. Min Act: -0.0000

Data Index: 2416 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1112351 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5041. Min Act: -0.0000

Data Index: 794366 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4854. Min Act: -0.0000

Data Index: 902139 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4717. Min Act: -0.0000

Data Index: 507404 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4498. Min Act: -0.0000

Data Index: 581938 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1094762 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1098746 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4536. Min Act: -0.0000

Data Index: 37913 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5096. Min Act: -0.0000

Data Index: 537299 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4492. Min Act: -0.0000

Data Index: 491832 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4779. Min Act: -0.0000

Data Index: 282602 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4481. Min Act: -0.0000

Data Index: 758723 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4368. Min Act: -0.0000

Data Index: 685536 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4139. Min Act: -0.0000

Data Index: 728870 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4107. Min Act: -0.0000

Data Index: 693222 (C4 (Web Text))

Max Activating Token Index: 115