Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3202 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1126709 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1044. Min Act: -0.0000

Data Index: 393408 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1117. Min Act: -0.0000

Data Index: 215964 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1901224 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1875159 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0957. Min Act: -0.0000

Data Index: 232267 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0897. Min Act: -0.0000

Data Index: 501292 (The Pile)

Max Activating Token Index: 437

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1589403 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0800. Min Act: -0.0000

Data Index: 385038 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0793. Min Act: -0.0000

Data Index: 781109 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1745324 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1844585 (The Pile)

Max Activating Token Index: 856

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1674823 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0795. Min Act: -0.0000

Data Index: 499584 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1694297 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0774. Min Act: -0.0000

Data Index: 129507 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0777. Min Act: -0.0000

Data Index: 484857 (The Pile)

Max Activating Token Index: 534

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1267891 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0768. Min Act: -0.0000

Data Index: 957225 (The Pile)

Max Activating Token Index: 275

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1973929 (The Pile)

Max Activating Token Index: 457