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

Dataset: The Pile

Neuron 1861 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: 1.6871. Min Range: -1.6871

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1752886 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1497670 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1117557 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1592834 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.5736. Min Act: -0.0000

Data Index: 540101 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.4217. Min Act: -0.0000

Data Index: 350426 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.3867. Min Act: -0.0000

Data Index: 936129 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.5601. Min Act: -0.0000

Data Index: 880874 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1153848 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1101938 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2565. Min Act: -0.0000

Data Index: 184656 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1702988 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1086365 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1245688 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.1175. Min Act: -0.0000

Data Index: 361324 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1500563 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.1200. Min Act: -0.0000

Data Index: 143191 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1889056 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1899246 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 1.6871. Min Range: -1.6871

Max Act: 1.2873. Min Act: -0.0000

Data Index: 1659674 (The Pile)

Max Activating Token Index: 510