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

Dataset: The Pile

Neuron 3077 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: 0.6326. Min Range: -0.6326

Max Act: 0.6326. Min Act: -0.0000

Data Index: 856806 (The Pile)

Max Activating Token Index: 896

Text #1

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1569246 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1536945 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5600. Min Act: -0.0000

Data Index: 130107 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1951394 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1960007 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1732427 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1042393 (The Pile)

Max Activating Token Index: 746

Text #8

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1094484 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1695655 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4954. Min Act: -0.0000

Data Index: 212890 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1470357 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1125832 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4539. Min Act: -0.0000

Data Index: 933486 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1345342 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1078024 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1231012 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1738794 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1541814 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.6326. Min Range: -0.6326

Max Act: 0.4388. Min Act: -0.0000

Data Index: 569985 (The Pile)

Max Activating Token Index: 971