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

Dataset: The Pile

Neuron 812 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: 0.5667. Min Range: -0.5667

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1833073 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5170. Min Act: -0.0000

Data Index: 878116 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5455. Min Act: -0.0000

Data Index: 429975 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5244. Min Act: -0.0000

Data Index: 768053 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1337187 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1979261 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5386. Min Act: -0.0000

Data Index: 131379 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5077. Min Act: -0.0000

Data Index: 557264 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5227. Min Act: -0.0000

Data Index: 381340 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5005. Min Act: -0.0000

Data Index: 284485 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1366287 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1813787 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5076. Min Act: -0.0000

Data Index: 803371 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4617. Min Act: -0.0000

Data Index: 898860 (The Pile)

Max Activating Token Index: 320

Text #14

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1063282 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1833859 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1124251 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1986241 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1333933 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1394907 (The Pile)

Max Activating Token Index: 993