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

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

Neuron 1901 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.1324. Min Act: -0.0000

Data Index: 153674 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1072178 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9914. Min Act: -0.0000

Data Index: 802830 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0051. Min Act: -0.0000

Data Index: 236539 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1067691 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1128158 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0047. Min Act: -0.0000

Data Index: 666095 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9239. Min Act: -0.0000

Data Index: 661165 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8277. Min Act: -0.0000

Data Index: 319141 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8534. Min Act: -0.0000

Data Index: 823508 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7786. Min Act: -0.0000

Data Index: 74777 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7514. Min Act: -0.0000

Data Index: 126597 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7014. Min Act: -0.0000

Data Index: 425260 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.6741. Min Act: -0.0000

Data Index: 993526 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8100. Min Act: -0.0000

Data Index: 667513 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1341256 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7869. Min Act: -0.0000

Data Index: 13826 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7421. Min Act: -0.0000

Data Index: 677290 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.6659. Min Act: -0.0000

Data Index: 929760 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.6406. Min Act: -0.0000

Data Index: 947486 (C4 (Web Text))

Max Activating Token Index: 759