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

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

Neuron 5327 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.6665. Min Act: -0.0000

Data Index: 1052292 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.9741. Min Act: -0.0000

Data Index: 971791 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.6588. Min Act: -0.0000

Data Index: 983821 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.6377. Min Act: -0.0000

Data Index: 271695 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.7888. Min Act: -0.0000

Data Index: 113222 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.5696. Min Act: -0.0000

Data Index: 932948 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.4881. Min Act: -0.0000

Data Index: 1096294 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.4883. Min Act: -0.0000

Data Index: 28994 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.4726. Min Act: -0.0000

Data Index: 998080 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.6258. Min Act: -0.0000

Data Index: 653026 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.5066. Min Act: -0.0000

Data Index: 1181315 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.3237. Min Act: -0.0000

Data Index: 821987 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.4716. Min Act: -0.0000

Data Index: 178333 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.3128. Min Act: -0.0000

Data Index: 1025951 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.3258. Min Act: -0.0000

Data Index: 418161 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.3309. Min Act: -0.0000

Data Index: 381200 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.1654. Min Act: -0.0000

Data Index: 891482 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 3.9741. Min Range: -3.9741

Max Act: 3.0081. Min Act: -0.0000

Data Index: 388751 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.9741. Min Range: -3.9741

Max Act: 2.8512. Min Act: -0.0000

Data Index: 1415967 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 3.9741. Min Range: -3.9741

Max Act: 2.9630. Min Act: -0.0000

Data Index: 796288 (C4 (Web Text))

Max Activating Token Index: 168