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

Dataset: The Pile

Neuron 4953 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: 0.8008. Min Range: -0.8008

Max Act: 0.8008. Min Act: -0.0000

Data Index: 796241 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6591. Min Act: -0.0000

Data Index: 558318 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1680819 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1936694 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1127998 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1594943 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1230335 (The Pile)

Max Activating Token Index: 922

Text #7

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5777. Min Act: -0.0000

Data Index: 724856 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1020479 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6032. Min Act: -0.0000

Data Index: 340133 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5776. Min Act: -0.0000

Data Index: 714255 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5308. Min Act: -0.0000

Data Index: 750351 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5798. Min Act: -0.0000

Data Index: 794642 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5635. Min Act: -0.0000

Data Index: 253097 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1967637 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1048259 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1641591 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4642. Min Act: -0.0000

Data Index: 95843 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1087404 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1936512 (The Pile)

Max Activating Token Index: 171