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

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

Neuron 3863 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.8850. Min Act: -0.0000

Data Index: 747223 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6814. Min Act: -0.0000

Data Index: 313409 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.7020. Min Act: -0.0000

Data Index: 545521 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1296393 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.7383. Min Act: -0.0000

Data Index: 159102 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1145166 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.7146. Min Act: -0.0000

Data Index: 292604 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5648. Min Act: -0.0000

Data Index: 1252319 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6989. Min Act: -0.0000

Data Index: 1112012 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5505. Min Act: -0.0000

Data Index: 862846 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6823. Min Act: -0.0000

Data Index: 1163157 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6720. Min Act: -0.0000

Data Index: 12570 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1318237 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1077553 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5747. Min Act: -0.0000

Data Index: 650591 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5797. Min Act: -0.0000

Data Index: 914368 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5587. Min Act: -0.0000

Data Index: 401185 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.4431. Min Act: -0.0000

Data Index: 241713 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.6824. Min Act: -0.0000

Data Index: 60840 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 2.8850. Min Range: -2.8850

Max Act: 2.5429. Min Act: -0.0000

Data Index: 682771 (C4 (Web Text))

Max Activating Token Index: 603