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

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

Neuron 4635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1007822 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5655. Min Act: -0.0000

Data Index: 700576 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6203. Min Act: -0.0000

Data Index: 630957 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4005. Min Act: -0.0000

Data Index: 680837 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1077715 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1278920 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5527. Min Act: -0.0000

Data Index: 319363 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4914. Min Act: -0.0000

Data Index: 839458 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4604. Min Act: -0.0000

Data Index: 275114 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6779. Min Act: -0.0000

Data Index: 990241 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5779. Min Act: -0.0001

Data Index: 653845 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5759. Min Act: -0.0000

Data Index: 932718 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1272028 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5635. Min Act: -0.0000

Data Index: 468568 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5042. Min Act: -0.0000

Data Index: 535221 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1337570 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5627. Min Act: -0.0000

Data Index: 336214 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1181089 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5274. Min Act: -0.0000

Data Index: 578314 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6485. Min Act: -0.0000

Data Index: 797230 (C4 (Web Text))

Max Activating Token Index: 925