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

Dataset: The Pile

Neuron 4771 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: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1688941 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0791. Min Act: -0.0000

Data Index: 599692 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1386440 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1187219 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0608. Min Act: -0.0000

Data Index: 146880 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1602048 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0547. Min Act: -0.0000

Data Index: 79525 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0539. Min Act: -0.0000

Data Index: 491008 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1003712 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1832535 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0643. Min Act: -0.0000

Data Index: 826265 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1761408 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1272791 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0645. Min Act: -0.0000

Data Index: 408356 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1025355 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0536. Min Act: -0.0000

Data Index: 1255356 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1973192 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1660309 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1106657 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1330765 (The Pile)

Max Activating Token Index: 117