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

Dataset: The Pile

Neuron 2387 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: 1.0918. Min Range: -1.0918

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1652810 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1009314 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1528504 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9174. Min Act: -0.0000

Data Index: 767839 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1455286 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8634. Min Act: 0.0000

Data Index: 946891 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1254293 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8701. Min Act: -0.0000

Data Index: 265097 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8334. Min Act: 0.0000

Data Index: 1980709 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7860. Min Act: -0.0000

Data Index: 978402 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8165. Min Act: -0.0000

Data Index: 602032 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1249263 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7619. Min Act: -0.0000

Data Index: 763148 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1764323 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1964288 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7140. Min Act: -0.0000

Data Index: 375371 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6779. Min Act: 0.0000

Data Index: 170881 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1694149 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7205. Min Act: 0.0000

Data Index: 1953360 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1477435 (The Pile)

Max Activating Token Index: 352