Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6101 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.6069. Min Act: -0.0000

Data Index: 546877 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1300934 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4708. Min Act: -0.0000

Data Index: 514045 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1069763 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3616. Min Act: -0.0000

Data Index: 1331498 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2856. Min Act: -0.0000

Data Index: 377640 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2832. Min Act: -0.0000

Data Index: 146157 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1597. Min Act: -0.0000

Data Index: 950072 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1923. Min Act: -0.0000

Data Index: 968090 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1175. Min Act: -0.0000

Data Index: 401620 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0972. Min Act: -0.0000

Data Index: 498503 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1557. Min Act: -0.0000

Data Index: 53276 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0825. Min Act: -0.0000

Data Index: 81547 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1397. Min Act: -0.0000

Data Index: 602643 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1366. Min Act: -0.0000

Data Index: 737377 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1099185 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1196. Min Act: -0.0000

Data Index: 980443 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1262177 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0805. Min Act: -0.0000

Data Index: 273691 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1120786 (C4 (Web Text))

Max Activating Token Index: 387