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

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

Neuron 3592 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: 1.8746. Min Range: -1.8746

Max Act: 1.8746. Min Act: -0.0000

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.4486. Min Act: -0.0000

Data Index: 39942 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.3981. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.5251. Min Act: -0.0000

Data Index: 987733 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.3525. Min Act: -0.0000

Data Index: 216914 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.4552. Min Act: -0.0000

Data Index: 633839 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2504. Min Act: -0.0000

Data Index: 626186 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.4059. Min Act: -0.0000

Data Index: 967028 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1351841 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2918. Min Act: -0.0000

Data Index: 408594 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1168524 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.1827. Min Act: -0.0000

Data Index: 396137 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1320752 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1328419 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2138. Min Act: -0.0000

Data Index: 136895 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.1299. Min Act: -0.0000

Data Index: 481903 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1322853 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.1871. Min Act: -0.0000

Data Index: 687721 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.8746. Min Range: -1.8746

Max Act: 1.1413. Min Act: -0.0000

Data Index: 25838 (C4 (Web Text))

Max Activating Token Index: 541