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

Dataset: The Pile

Neuron 2961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5567. Min Act: -0.0000

Data Index: 636326 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5495. Min Act: -0.0000

Data Index: 108666 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4974. Min Act: -0.0000

Data Index: 765493 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1467850 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1393721 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1758469 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4565. Min Act: -0.0000

Data Index: 47485 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1842960 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1994271 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4763. Min Act: -0.0000

Data Index: 97344 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1076617 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1428179 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4342. Min Act: -0.0000

Data Index: 287964 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4289. Min Act: -0.0000

Data Index: 722927 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4301. Min Act: -0.0000

Data Index: 976682 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4138. Min Act: -0.0000

Data Index: 115326 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4239. Min Act: -0.0000

Data Index: 854800 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4372. Min Act: -0.0000

Data Index: 172879 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1666183 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1184423 (The Pile)

Max Activating Token Index: 360