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

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

Neuron 4390 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: 0.3099. Min Range: -0.3099

Max Act: 0.2770. Min Act: -0.0000

Data Index: 220194 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0000

Data Index: 776851 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2666. Min Act: -0.0000

Data Index: 464268 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2360. Min Act: -0.0000

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2173. Min Act: -0.0000

Data Index: 355072 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2043. Min Act: -0.0000

Data Index: 310792 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2118. Min Act: -0.0000

Data Index: 938170 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1919. Min Act: -0.0000

Data Index: 908388 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2172. Min Act: -0.0000

Data Index: 541052 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1913. Min Act: -0.0000

Data Index: 321781 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1276923 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1996. Min Act: -0.0000

Data Index: 524868 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1993. Min Act: -0.0000

Data Index: 378285 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2048. Min Act: -0.0000

Data Index: 96851 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1989. Min Act: -0.0000

Data Index: 878764 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1941. Min Act: -0.0000

Data Index: 563437 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1716. Min Act: -0.0000

Data Index: 758039 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1882. Min Act: -0.0000

Data Index: 390135 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1975. Min Act: -0.0000

Data Index: 768738 (C4 (Web Text))

Max Activating Token Index: 143