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

Dataset: The Pile

Neuron 4510 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: 0.2230. Min Range: -0.2230

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1741295 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.2061. Min Act: -0.0000

Data Index: 152255 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.2117. Min Act: -0.0000

Data Index: 775225 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.2079. Min Act: -0.0000

Data Index: 595647 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.2013. Min Act: -0.0000

Data Index: 596463 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1554928 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1733711 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1528779 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1867. Min Act: -0.0000

Data Index: 685924 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1354189 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1671138 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1882. Min Act: -0.0000

Data Index: 635245 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1920587 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1824. Min Act: -0.0000

Data Index: 968529 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1833812 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1853. Min Act: -0.0000

Data Index: 296802 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1434386 (The Pile)

Max Activating Token Index: 241

Text #17

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1697231 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1117469 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.2230. Min Range: -0.2230

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1914770 (The Pile)

Max Activating Token Index: 144