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

Dataset: The Pile

Neuron 3419 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0989. Min Range: -1.0989

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1911425 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1957382 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1982388 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.8600. Min Act: -0.0000

Data Index: 995389 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7995. Min Act: -0.0000

Data Index: 171657 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7384. Min Act: -0.0000

Data Index: 474282 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1792386 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1099413 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1156021 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.6829. Min Act: -0.0000

Data Index: 814000 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7590. Min Act: -0.0000

Data Index: 976139 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1845024 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7781. Min Act: -0.0000

Data Index: 901975 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7237. Min Act: -0.0000

Data Index: 461014 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1770564 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1472462 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7128. Min Act: -0.0000

Data Index: 91483 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1371091 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7311. Min Act: 0.0000

Data Index: 549214 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 1.0989. Min Range: -1.0989

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1029804 (The Pile)

Max Activating Token Index: 69