Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1914. Min Act: -0.0001

Data Index: 1000712 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.2656. Min Act: -0.0001

Data Index: 1170037 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.2078. Min Act: -0.0001

Data Index: 321795 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.1316. Min Act: -0.0001

Data Index: 167365 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0819. Min Act: -0.0001

Data Index: 844230 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0692. Min Act: -0.0001

Data Index: 1349663 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 1.2656. Min Range: -1.2656

Max Act: 1.0452. Min Act: -0.0001

Data Index: 884822 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9757. Min Act: -0.0001

Data Index: 584806 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9396. Min Act: -0.0001

Data Index: 1126345 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8731. Min Act: -0.0001

Data Index: 181830 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8913. Min Act: -0.0001

Data Index: 574053 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9496. Min Act: -0.0001

Data Index: 280818 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8819. Min Act: -0.0001

Data Index: 1278656 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8619. Min Act: -0.0001

Data Index: 734694 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9107. Min Act: -0.0001

Data Index: 972299 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8558. Min Act: -0.0001

Data Index: 502792 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8838. Min Act: -0.0001

Data Index: 868847 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8485. Min Act: -0.0001

Data Index: 373270 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.8760. Min Act: -0.0001

Data Index: 855219 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.2656. Min Range: -1.2656

Max Act: 0.9004. Min Act: -0.0001

Data Index: 978672 (C4 (Web Text))

Max Activating Token Index: 995