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

Dataset: The Pile

Neuron 2058 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: 0.9785. Min Range: -0.9785

Max Act: 0.9785. Min Act: -0.0000

Data Index: 665013 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1670079 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1746493 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1041535 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1925081 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1837554 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1905844 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8341. Min Act: -0.0000

Data Index: 324849 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8253. Min Act: -0.0000

Data Index: 231148 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7910. Min Act: -0.0000

Data Index: 986472 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1552042 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1495356 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1964199 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8156. Min Act: -0.0000

Data Index: 89599 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1136487 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8066. Min Act: -0.0000

Data Index: 606586 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1318833 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8176. Min Act: -0.0000

Data Index: 683255 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1094850 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.9785. Min Range: -0.9785

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1235479 (The Pile)

Max Activating Token Index: 294