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

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

Neuron 190 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.8136. Min Act: -0.0000

Data Index: 49576 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1053843 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1312716 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6414. Min Act: -0.0000

Data Index: 410801 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1016060 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6255. Min Act: -0.0000

Data Index: 421073 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1058609 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1127974 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6001. Min Act: -0.0000

Data Index: 373339 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5977. Min Act: -0.0000

Data Index: 707493 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5654. Min Act: -0.0000

Data Index: 308898 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5401. Min Act: -0.0000

Data Index: 422605 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5305. Min Act: -0.0000

Data Index: 894893 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.6178. Min Act: -0.0000

Data Index: 223123 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.5689. Min Act: -0.0000

Data Index: 1172633 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.3914. Min Act: -0.0000

Data Index: 935264 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.3755. Min Act: -0.0000

Data Index: 1004372 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1066903 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.4263. Min Act: -0.0000

Data Index: 299688 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.8136. Min Range: -1.8136

Max Act: 1.3389. Min Act: -0.0000

Data Index: 271330 (C4 (Web Text))

Max Activating Token Index: 719