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

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

Neuron 3970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1359552 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.3145. Min Act: -0.0000

Data Index: 888132 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2835. Min Act: -0.0000

Data Index: 61260 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1175894 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2692. Min Act: -0.0000

Data Index: 1333621 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2633. Min Act: -0.0000

Data Index: 398353 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2365. Min Act: -0.0000

Data Index: 163786 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2649. Min Act: -0.0000

Data Index: 548962 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2336. Min Act: -0.0000

Data Index: 175879 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2107. Min Act: -0.0000

Data Index: 210155 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1136085 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2169. Min Act: -0.0000

Data Index: 585308 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1207851 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2077. Min Act: -0.0000

Data Index: 775207 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.1845. Min Act: -0.0000

Data Index: 227621 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2042. Min Act: -0.0000

Data Index: 884836 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2089. Min Act: -0.0000

Data Index: 843029 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2010. Min Act: -0.0000

Data Index: 383644 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1198659 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2023. Min Act: -0.0000

Data Index: 921931 (C4 (Web Text))

Max Activating Token Index: 857