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

Dataset: The Pile

Neuron 1961 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: 5.6055. Min Range: -5.6055

Max Act: 5.4604. Min Act: -0.0000

Data Index: 1388053 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.6055. Min Act: -0.0000

Data Index: 33660 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.9741. Min Act: -0.0000

Data Index: 460561 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.1375. Min Act: -0.0000

Data Index: 1216483 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.1795. Min Act: -0.0000

Data Index: 1939621 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.4190. Min Act: -0.0000

Data Index: 71599 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.0658. Min Act: -0.0000

Data Index: 757226 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.9837. Min Act: -0.0000

Data Index: 1603069 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.8274. Min Act: -0.0000

Data Index: 1591804 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.1280. Min Act: -0.0000

Data Index: 1626870 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 5.6055. Min Range: -5.6055

Max Act: 5.3083. Min Act: -0.0000

Data Index: 1861097 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.5562. Min Act: -0.0000

Data Index: 1290639 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.7002. Min Act: -0.0000

Data Index: 783287 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.8174. Min Act: -0.0000

Data Index: 1894866 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.9930. Min Act: -0.0000

Data Index: 450902 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.8078. Min Act: -0.0000

Data Index: 1909765 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.9824. Min Act: -0.0000

Data Index: 587677 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.8100. Min Act: -0.0000

Data Index: 456581 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.6087. Min Act: -0.0000

Data Index: 391251 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 5.6055. Min Range: -5.6055

Max Act: 4.6120. Min Act: -0.0000

Data Index: 1332418 (The Pile)

Max Activating Token Index: 492