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

Dataset: The Pile

Neuron 462 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1862276 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3716. Min Act: -0.0000

Data Index: 725872 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1827718 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1335624 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3112. Min Act: -0.0000

Data Index: 476670 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1997355 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2954. Min Act: -0.0000

Data Index: 944605 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3738. Min Act: -0.0000

Data Index: 1279961 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1769614 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1831722 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2267. Min Act: -0.0000

Data Index: 248425 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1392498 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1249324 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2053. Min Act: -0.0000

Data Index: 449504 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1540122 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.2075. Min Act: 0.0000

Data Index: 1221620 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1555504 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1119663 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1802. Min Act: -0.0000

Data Index: 121568 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 1.3738. Min Range: -1.3738

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1482796 (The Pile)

Max Activating Token Index: 926