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

Dataset: The Pile

Neuron 2368 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: 0.9139. Min Range: -0.9139

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1128030 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1376926 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1396108 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6813. Min Act: -0.0000

Data Index: 182146 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1854142 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1091332 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5963. Min Act: -0.0000

Data Index: 188401 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6077. Min Act: -0.0000

Data Index: 170005 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5602. Min Act: -0.0000

Data Index: 662086 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1663896 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5652. Min Act: -0.0000

Data Index: 225282 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1110535 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5507. Min Act: -0.0000

Data Index: 560754 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1101479 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5309. Min Act: -0.0000

Data Index: 511434 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1084895 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1598825 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1661444 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5164. Min Act: -0.0000

Data Index: 162702 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5198. Min Act: -0.0000

Data Index: 594899 (The Pile)

Max Activating Token Index: 240