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

Dataset: The Pile

Neuron 77 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: 0.5807. Min Range: -0.5807

Max Act: 0.5807. Min Act: -0.0000

Data Index: 546462 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1509885 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4579. Min Act: -0.0000

Data Index: 810102 (The Pile)

Max Activating Token Index: 391

Text #3

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1729559 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1716469 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4548. Min Act: -0.0000

Data Index: 434966 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1033933 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1763935 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1463459 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4434. Min Act: -0.0000

Data Index: 804589 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4082. Min Act: -0.0000

Data Index: 638044 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1563644 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1540240 (The Pile)

Max Activating Token Index: 68

Text #13

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1523821 (The Pile)

Max Activating Token Index: 79

Text #14

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1409975 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1928464 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3985. Min Act: -0.0000

Data Index: 499751 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1405561 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3833. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.3786. Min Act: -0.0000

Data Index: 263934 (The Pile)

Max Activating Token Index: 888