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

Dataset: The Pile

Neuron 1215 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: 0.2903. Min Range: -0.2903

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1344061 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1909254 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2654. Min Act: -0.0000

Data Index: 19626 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2758. Min Act: -0.0000

Data Index: 377866 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1999261 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1541930 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1410513 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2458. Min Act: -0.0000

Data Index: 465844 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1361485 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1738066 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1775785 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1474760 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1473092 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1223514 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1512202 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1743932 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1428939 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2193. Min Act: -0.0000

Data Index: 697219 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2144. Min Act: -0.0000

Data Index: 99717 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.2903. Min Range: -0.2903

Max Act: 0.2167. Min Act: -0.0000

Data Index: 513555 (The Pile)

Max Activating Token Index: 465