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

Dataset: The Pile

Neuron 4459 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: 3.9752. Min Range: -3.9752

Max Act: 3.9752. Min Act: -0.0000

Data Index: 1638680 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.8367. Min Act: -0.0000

Data Index: 636988 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.7743. Min Act: -0.0000

Data Index: 1503822 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.7024. Min Act: -0.0000

Data Index: 370580 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.5978. Min Act: -0.0000

Data Index: 574236 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.6734. Min Act: -0.0000

Data Index: 415784 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.6633. Min Act: -0.0000

Data Index: 1321856 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.4465. Min Act: -0.0000

Data Index: 1131700 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.2546. Min Act: -0.0000

Data Index: 823957 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.5060. Min Act: -0.0000

Data Index: 1677853 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.3531. Min Act: -0.0000

Data Index: 1052220 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.4761. Min Act: -0.0000

Data Index: 314199 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.3216. Min Act: -0.0000

Data Index: 1491612 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.3076. Min Act: -0.0000

Data Index: 592883 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.2993. Min Act: -0.0000

Data Index: 1648318 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.1762. Min Act: -0.0000

Data Index: 1905023 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.4351. Min Act: -0.0000

Data Index: 947440 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 3.9752. Min Range: -3.9752

Max Act: 2.9197. Min Act: -0.0000

Data Index: 1467973 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 3.9752. Min Range: -3.9752

Max Act: 2.9094. Min Act: -0.0000

Data Index: 276825 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 3.9752. Min Range: -3.9752

Max Act: 3.2408. Min Act: -0.0000

Data Index: 1719364 (The Pile)

Max Activating Token Index: 552