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

Dataset: The Pile

Neuron 500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1968694 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0960. Min Act: -0.0000

Data Index: 827505 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0956. Min Act: -0.0000

Data Index: 929619 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1742072 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0853. Min Act: -0.0000

Data Index: 752871 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1437993 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0863. Min Act: -0.0000

Data Index: 971739 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0809. Min Act: -0.0000

Data Index: 848086 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1081515 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1761934 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0794. Min Act: -0.0000

Data Index: 493755 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0706. Min Act: -0.0000

Data Index: 344676 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1811891 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0706. Min Act: -0.0000

Data Index: 780153 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0705. Min Act: -0.0000

Data Index: 641319 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0761. Min Act: -0.0000

Data Index: 665962 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1611046 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1684727 (The Pile)

Max Activating Token Index: 28

Text #18

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0690. Min Act: -0.0000

Data Index: 299819 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0695. Min Act: -0.0000

Data Index: 130059 (The Pile)

Max Activating Token Index: 465