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

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

Neuron 1895 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: 1.3822. Min Range: -1.3822

Max Act: 1.3711. Min Act: -0.0000

Data Index: 622431 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1077192 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1309899 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.2220. Min Act: -0.0000

Data Index: 746439 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.2333. Min Act: -0.0000

Data Index: 65186 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1277850 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1017927 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1559. Min Act: -0.0000

Data Index: 953222 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1254246 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1020. Min Act: -0.0000

Data Index: 415475 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1108. Min Act: -0.0000

Data Index: 658193 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1042. Min Act: -0.0000

Data Index: 477067 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1782. Min Act: -0.0000

Data Index: 770286 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.1014. Min Act: -0.0000

Data Index: 957335 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0526. Min Act: -0.0000

Data Index: 910747 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1114151 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0268. Min Act: -0.0000

Data Index: 773676 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3822. Min Range: -1.3822

Max Act: 0.9630. Min Act: -0.0000

Data Index: 884900 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0386. Min Act: -0.0000

Data Index: 366675 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.3822. Min Range: -1.3822

Max Act: 1.0704. Min Act: -0.0000

Data Index: 608509 (C4 (Web Text))

Max Activating Token Index: 733