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

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

Neuron 5007 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: 0.7780. Min Range: -0.7780

Max Act: 0.7780. Min Act: -0.0000

Data Index: 448114 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5318. Min Act: -0.0000

Data Index: 205760 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5069. Min Act: -0.0000

Data Index: 370616 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5325. Min Act: -0.0000

Data Index: 46569 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5501. Min Act: -0.0000

Data Index: 553378 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5289. Min Act: -0.0000

Data Index: 964388 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1347678 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1163823 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5292. Min Act: -0.0000

Data Index: 757333 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1282289 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5228. Min Act: -0.0000

Data Index: 539689 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4911. Min Act: -0.0000

Data Index: 260408 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4630. Min Act: -0.0000

Data Index: 500184 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4753. Min Act: -0.0000

Data Index: 85093 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.5090. Min Act: -0.0000

Data Index: 881797 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1072712 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4363. Min Act: -0.0000

Data Index: 392357 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4528. Min Act: -0.0000

Data Index: 400629 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.7780. Min Range: -0.7780

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1167253 (C4 (Web Text))

Max Activating Token Index: 425