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

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

Neuron 5733 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.4235. Min Act: -0.0000

Data Index: 708049 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.4437. Min Act: -0.0000

Data Index: 970443 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.4239. Min Act: -0.0000

Data Index: 894829 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1288850 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.2966. Min Act: -0.0000

Data Index: 76093 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.5067. Min Act: -0.0000

Data Index: 929414 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1262050 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.1501. Min Act: -0.0000

Data Index: 564893 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1212695 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.0684. Min Act: -0.0000

Data Index: 1112482 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1005700 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1093175 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.9986. Min Act: -0.0000

Data Index: 351845 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.0018. Min Act: -0.0000

Data Index: 630673 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1130321 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 1.5067. Min Range: -1.5067

Max Act: 1.1127. Min Act: -0.0000

Data Index: 340145 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1215720 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1254661 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1117508 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.5067. Min Range: -1.5067

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1303601 (C4 (Web Text))

Max Activating Token Index: 528