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

Dataset: The Pile

Neuron 215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1630787 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1432028 (The Pile)

Max Activating Token Index: 507

Text #2

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1528984 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4222. Min Act: -0.0000

Data Index: 695344 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4919. Min Act: -0.0000

Data Index: 163505 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1827016 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4003. Min Act: -0.0000

Data Index: 909201 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1808519 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1909710 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4257. Min Act: -0.0000

Data Index: 763370 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1140164 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1005045 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3981. Min Act: -0.0000

Data Index: 233687 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1642627 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1470882 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1559561 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3705. Min Act: -0.0000

Data Index: 73094 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1119463 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1729454 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1434158 (The Pile)

Max Activating Token Index: 211