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

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

Neuron 1496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0002

Data Index: 343790 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1007. Min Act: -0.0002

Data Index: 545600 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0998. Min Act: -0.0002

Data Index: 667575 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0940. Min Act: -0.0002

Data Index: 77850 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1229064 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0874. Min Act: -0.0002

Data Index: 848522 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1080887 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1358253 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0838. Min Act: -0.0002

Data Index: 546915 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0801. Min Act: -0.0002

Data Index: 862350 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0767. Min Act: -0.0002

Data Index: 956125 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0764. Min Act: -0.0002

Data Index: 846494 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1088690 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1308334 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0654. Min Act: -0.0002

Data Index: 473355 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0640. Min Act: -0.0002

Data Index: 84958 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0631. Min Act: -0.0002

Data Index: 141701 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0650. Min Act: -0.0002

Data Index: 387343 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0641. Min Act: -0.0002

Data Index: 275252 (C4 (Web Text))

Max Activating Token Index: 399