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

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

Neuron 3076 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2235. Min Range: -2.2235

Max Act: 2.2235. Min Act: -0.0000

Data Index: 234664 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 2.2235. Min Range: -2.2235

Max Act: 2.1400. Min Act: -0.0000

Data Index: 912808 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 2.2235. Min Range: -2.2235

Max Act: 2.0537. Min Act: -0.0000

Data Index: 257921 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1080516 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.7478. Min Act: -0.0000

Data Index: 233903 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.8648. Min Act: -0.0000

Data Index: 767121 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.7942. Min Act: -0.0000

Data Index: 222420 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1282541 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6155. Min Act: -0.0000

Data Index: 439900 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6679. Min Act: 0.0001

Data Index: 138571 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5691. Min Act: -0.0000

Data Index: 781426 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6838. Min Act: 0.0000

Data Index: 1100798 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.7193. Min Act: -0.0000

Data Index: 149191 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6716. Min Act: 0.0000

Data Index: 494360 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5980. Min Act: 0.0001

Data Index: 96147 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6499. Min Act: 0.0004

Data Index: 964280 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5984. Min Act: 0.0001

Data Index: 71717 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6438. Min Act: -0.0000

Data Index: 478002 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.6075. Min Act: -0.0000

Data Index: 188492 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 2.2235. Min Range: -2.2235

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1004120 (C4 (Web Text))

Max Activating Token Index: 296