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

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

Neuron 99 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.0849. Min Range: -8.0849

Max Act: 8.0849. Min Act: -0.0000

Data Index: 986625 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.8509. Min Act: -0.0000

Data Index: 168593 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.9359. Min Act: -0.0000

Data Index: 239408 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.7895. Min Act: -0.0000

Data Index: 1291033 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.6211. Min Act: -0.0000

Data Index: 411901 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.7988. Min Act: -0.0000

Data Index: 517127 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.6699. Min Act: -0.0000

Data Index: 671362 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.4307. Min Act: -0.0000

Data Index: 1179405 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.4068. Min Act: -0.0000

Data Index: 140258 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.2732. Min Act: -0.0000

Data Index: 485746 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.2174. Min Act: -0.0000

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.2170. Min Act: -0.0000

Data Index: 260199 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.3887. Min Act: -0.0000

Data Index: 1293369 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.0236. Min Act: -0.0000

Data Index: 185531 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 8.0849. Min Range: -8.0849

Max Act: 7.1302. Min Act: -0.0000

Data Index: 298515 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 8.0849. Min Range: -8.0849

Max Act: 6.6944. Min Act: -0.0000

Data Index: 280675 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 8.0849. Min Range: -8.0849

Max Act: 6.8576. Min Act: -0.0000

Data Index: 791067 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 8.0849. Min Range: -8.0849

Max Act: 6.8094. Min Act: -0.0000

Data Index: 1234362 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 8.0849. Min Range: -8.0849

Max Act: 6.9998. Min Act: -0.0000

Data Index: 999730 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 8.0849. Min Range: -8.0849

Max Act: 6.6110. Min Act: -0.0000

Data Index: 102043 (C4 (Web Text))

Max Activating Token Index: 141