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

Dataset: The Pile

Neuron 4065 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1240338 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5191. Min Act: -0.0000

Data Index: 496140 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.3916. Min Act: -0.0000

Data Index: 973017 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1408084 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4607. Min Act: -0.0000

Data Index: 285845 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.3576. Min Act: -0.0000

Data Index: 220983 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.2246. Min Act: -0.0000

Data Index: 312123 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.1696. Min Act: -0.0000

Data Index: 373311 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1626801 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1902003 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1841868 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1075152 (The Pile)

Max Activating Token Index: 589

Text #12

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.1193. Min Act: -0.0000

Data Index: 127083 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1787605 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.0192. Min Act: -0.0000

Data Index: 25902 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 1.6746. Min Range: -1.6746

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1411549 (The Pile)

Max Activating Token Index: 76

Text #16

Max Range: 1.6746. Min Range: -1.6746

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1358311 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.0244. Min Act: -0.0000

Data Index: 353260 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.6746. Min Range: -1.6746

Max Act: 0.9593. Min Act: -0.0000

Data Index: 815307 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1080309 (The Pile)

Max Activating Token Index: 325