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

Dataset: The Pile

Neuron 2054 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1309313 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1235813 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1965140 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6842. Min Act: -0.0000

Data Index: 406233 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6300. Min Act: -0.0000

Data Index: 560703 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1651821 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1451057 (The Pile)

Max Activating Token Index: 931

Text #7

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6236. Min Act: -0.0000

Data Index: 594185 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6805. Min Act: -0.0000

Data Index: 660875 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1701401 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5786. Min Act: -0.0000

Data Index: 483084 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5788. Min Act: -0.0000

Data Index: 467213 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5389. Min Act: -0.0000

Data Index: 346062 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.6442. Min Act: -0.0000

Data Index: 770808 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5941. Min Act: -0.0000

Data Index: 759620 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5577. Min Act: -0.0000

Data Index: 220187 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1198666 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1963030 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5831. Min Act: -0.0000

Data Index: 954753 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.7746. Min Range: -0.7746

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1491503 (The Pile)

Max Activating Token Index: 796