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

Dataset: The Pile

Neuron 518 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: 0.9797. Min Range: -0.9797

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1691689 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8254. Min Act: -0.0000

Data Index: 420666 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9005. Min Act: -0.0000

Data Index: 265959 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.9735. Min Act: -0.0000

Data Index: 933640 (The Pile)

Max Activating Token Index: 970

Text #4

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1786734 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7866. Min Act: -0.0000

Data Index: 681118 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1011590 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1739249 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7547. Min Act: -0.0000

Data Index: 670434 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1507422 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7335. Min Act: -0.0000

Data Index: 131368 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7757. Min Act: -0.0000

Data Index: 537785 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1544511 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7347. Min Act: -0.0000

Data Index: 654198 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7491. Min Act: -0.0000

Data Index: 156151 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7445. Min Act: -0.0000

Data Index: 398642 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7255. Min Act: -0.0000

Data Index: 836569 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7234. Min Act: -0.0000

Data Index: 176436 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1538222 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 0.9797. Min Range: -0.9797

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1536108 (The Pile)

Max Activating Token Index: 174