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

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

Neuron 4432 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: 0.9998. Min Range: -0.9998

Max Act: 0.9998. Min Act: -0.0000

Data Index: 776757 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7672. Min Act: -0.0000

Data Index: 951088 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8752. Min Act: -0.0000

Data Index: 241188 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7592. Min Act: -0.0000

Data Index: 519985 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7822. Min Act: -0.0000

Data Index: 877286 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6496. Min Act: -0.0000

Data Index: 860032 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.7010. Min Act: -0.0000

Data Index: 743774 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6468. Min Act: -0.0000

Data Index: 767460 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6274. Min Act: -0.0000

Data Index: 453447 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6257. Min Act: -0.0000

Data Index: 461857 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1160465 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6283. Min Act: -0.0000

Data Index: 594486 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5981. Min Act: -0.0000

Data Index: 655873 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1157529 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1304711 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6165. Min Act: -0.0000

Data Index: 723996 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1102823 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.6025. Min Act: -0.0000

Data Index: 721419 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5815. Min Act: -0.0000

Data Index: 795960 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.5617. Min Act: -0.0000

Data Index: 366610 (C4 (Web Text))

Max Activating Token Index: 990