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

Dataset: The Pile

Neuron 3314 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: 0.2571. Min Range: -0.2571

Max Act: 0.2559. Min Act: -0.0000

Data Index: 710964 (The Pile)

Max Activating Token Index: 920

Text #1

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1781640 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2266. Min Act: -0.0000

Data Index: 442819 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1117191 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2236. Min Act: -0.0000

Data Index: 333014 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1967733 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2135. Min Act: -0.0000

Data Index: 108132 (The Pile)

Max Activating Token Index: 845

Text #7

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1357104 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1888. Min Act: -0.0000

Data Index: 445842 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1249452 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1793. Min Act: -0.0000

Data Index: 237970 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1777. Min Act: -0.0000

Data Index: 891931 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1747744 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1141213 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2085. Min Act: -0.0000

Data Index: 362419 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1917. Min Act: -0.0000

Data Index: 760837 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1788. Min Act: -0.0000

Data Index: 460843 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1154393 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1822773 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1281239 (The Pile)

Max Activating Token Index: 913