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

Dataset: The Pile

Neuron 4063 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: 1.9754. Min Range: -1.9754

Max Act: 1.9754. Min Act: -0.0000

Data Index: 588466 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1065557 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.6875. Min Act: -0.0000

Data Index: 879834 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.5509. Min Act: -0.0000

Data Index: 740536 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4686. Min Act: -0.0000

Data Index: 97939 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.4715. Min Act: -0.0000

Data Index: 217726 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1542364 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.1432. Min Act: -0.0000

Data Index: 389577 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3492. Min Act: -0.0000

Data Index: 704632 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1697018 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3399. Min Act: -0.0000

Data Index: 960155 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3221. Min Act: -0.0000

Data Index: 537376 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1453739 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3980. Min Act: -0.0000

Data Index: 818971 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3941. Min Act: -0.0000

Data Index: 417600 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1185207 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1488714 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.2237. Min Act: -0.0000

Data Index: 555915 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.2738. Min Act: -0.0000

Data Index: 1141801 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.9754. Min Range: -1.9754

Max Act: 1.2734. Min Act: -0.0000

Data Index: 498523 (The Pile)

Max Activating Token Index: 416