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

Dataset: The Pile

Neuron 60 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: 0.9139. Min Range: -0.9139

Max Act: 0.8755. Min Act: -0.0000

Data Index: 540756 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.8677. Min Act: -0.0000

Data Index: 816979 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1913831 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.9139. Min Act: -0.0000

Data Index: 790586 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7046. Min Act: -0.0000

Data Index: 591915 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1487904 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1051567 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6977. Min Act: -0.0000

Data Index: 164500 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1688911 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6834. Min Act: -0.0000

Data Index: 163331 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1950207 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5824. Min Act: -0.0000

Data Index: 879625 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6531. Min Act: -0.0000

Data Index: 549014 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1992664 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1485366 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1293686 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6478. Min Act: -0.0000

Data Index: 433798 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1091839 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.6329. Min Act: -0.0000

Data Index: 950783 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.9139. Min Range: -0.9139

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1731940 (The Pile)

Max Activating Token Index: 980