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

Dataset: The Pile

Neuron 5072 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1939309 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2015. Min Act: -0.0000

Data Index: 858244 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1021366 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2092. Min Act: -0.0000

Data Index: 294199 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1957. Min Act: -0.0000

Data Index: 400426 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1973. Min Act: -0.0000

Data Index: 40228 (The Pile)

Max Activating Token Index: 467

Text #6

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1762212 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1890. Min Act: -0.0000

Data Index: 356919 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1948. Min Act: -0.0000

Data Index: 957033 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1793. Min Act: -0.0000

Data Index: 541068 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1462687 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1767. Min Act: -0.0000

Data Index: 225516 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1555451 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1800. Min Act: -0.0000

Data Index: 408034 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1087291 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1902 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1948585 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1820. Min Act: -0.0000

Data Index: 533087 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1730. Min Act: -0.0000

Data Index: 650269 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1612. Min Act: -0.0000

Data Index: 551638 (The Pile)

Max Activating Token Index: 719