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

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

Neuron 1964 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3902. Min Act: -0.0000

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1193956 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3026. Min Act: -0.0000

Data Index: 653458 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.3137. Min Act: -0.0000

Data Index: 24985 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2819. Min Act: -0.0000

Data Index: 773507 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1276176 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2562. Min Act: -0.0000

Data Index: 628117 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2667. Min Act: -0.0000

Data Index: 543425 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2422. Min Act: -0.0000

Data Index: 781037 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1305884 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1124057 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2220. Min Act: -0.0000

Data Index: 220528 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2050. Min Act: -0.0000

Data Index: 874795 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1312590 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.1953. Min Act: -0.0000

Data Index: 964985 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1082849 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2088. Min Act: -0.0000

Data Index: 719956 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.2032. Min Act: -0.0000

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.3902. Min Range: -0.3902

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1474571 (Python Code)

Max Activating Token Index: 48