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

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

Neuron 674 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.3000. Min Act: -0.0001

Data Index: 1203918 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2859. Min Act: -0.0000

Data Index: 547867 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2399. Min Act: -0.0001

Data Index: 535490 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2276. Min Act: -0.0001

Data Index: 266625 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2283. Min Act: -0.0000

Data Index: 921832 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2036. Min Act: -0.0001

Data Index: 154009 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2023. Min Act: -0.0001

Data Index: 549301 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1882. Min Act: -0.0001

Data Index: 696921 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1178443 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1775. Min Act: -0.0001

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1106247 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1767. Min Act: -0.0000

Data Index: 384635 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1772. Min Act: -0.0001

Data Index: 778389 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1578 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1800. Min Act: -0.0001

Data Index: 948153 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1743. Min Act: -0.0001

Data Index: 283052 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1730. Min Act: -0.0001

Data Index: 699612 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1781. Min Act: -0.0001

Data Index: 212757 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1824. Min Act: -0.0000

Data Index: 755826 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1174820 (C4 (Web Text))

Max Activating Token Index: 765