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

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

Neuron 4456 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: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0002

Data Index: 687861 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0907. Min Act: -0.0002

Data Index: 986340 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0881. Min Act: -0.0002

Data Index: 118164 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0854. Min Act: -0.0002

Data Index: 222068 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1287599 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0883. Min Act: -0.0002

Data Index: 510073 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1166472 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0847. Min Act: -0.0002

Data Index: 960021 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0783. Min Act: -0.0002

Data Index: 895940 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1052946 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0807. Min Act: -0.0002

Data Index: 923282 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1239043 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0832. Min Act: -0.0002

Data Index: 298336 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0829. Min Act: -0.0002

Data Index: 205573 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1203069 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0824. Min Act: -0.0002

Data Index: 374534 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1239958 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0788. Min Act: -0.0002

Data Index: 287757 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0785. Min Act: -0.0002

Data Index: 953189 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1067806 (C4 (Web Text))

Max Activating Token Index: 686