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

Dataset: The Pile

Neuron 1589 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1987881 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.4530. Min Act: 0.0000

Data Index: 1626314 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.4494. Min Act: -0.0000

Data Index: 889776 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1915591 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1231720 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.2553. Min Act: -0.0000

Data Index: 1462355 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1908074 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.2438. Min Act: -0.0000

Data Index: 247754 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1049174 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1257. Min Act: -0.0000

Data Index: 907548 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1460. Min Act: -0.0000

Data Index: 899764 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1816. Min Act: -0.0000

Data Index: 1350533 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1884771 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.0722. Min Act: -0.0000

Data Index: 360909 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 1.6754. Min Range: -1.6754

Max Act: 0.9734. Min Act: -0.0000

Data Index: 560953 (The Pile)

Max Activating Token Index: 628

Text #15

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1607306 (The Pile)

Max Activating Token Index: 510

Text #16

Max Range: 1.6754. Min Range: -1.6754

Max Act: 0.9889. Min Act: -0.0000

Data Index: 705865 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1068799 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 1.6754. Min Range: -1.6754

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1015966 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 1.6754. Min Range: -1.6754

Max Act: 1.0225. Min Act: -0.0000

Data Index: 955219 (The Pile)

Max Activating Token Index: 561