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

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

Neuron 2680 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: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1234796 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2080. Min Act: -0.0000

Data Index: 566829 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1978. Min Act: -0.0000

Data Index: 897503 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1900. Min Act: -0.0000

Data Index: 117531 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1877. Min Act: -0.0000

Data Index: 688337 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1690. Min Act: -0.0000

Data Index: 269136 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1205670 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1748. Min Act: -0.0000

Data Index: 25796 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1066378 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1781. Min Act: -0.0000

Data Index: 224831 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1773. Min Act: -0.0000

Data Index: 512492 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1760. Min Act: -0.0000

Data Index: 333775 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1677. Min Act: -0.0000

Data Index: 685239 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1709. Min Act: -0.0000

Data Index: 659114 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1726. Min Act: -0.0000

Data Index: 82214 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1651. Min Act: -0.0000

Data Index: 597538 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1727. Min Act: -0.0000

Data Index: 516624 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1596. Min Act: -0.0000

Data Index: 931100 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1041887 (C4 (Web Text))

Max Activating Token Index: 748