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

Dataset: The Pile

Neuron 2386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1532752 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.4228. Min Act: -0.0000

Data Index: 664624 (The Pile)

Max Activating Token Index: 983

Text #2

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1203762 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.3108. Min Act: -0.0000

Data Index: 413544 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1022455 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1999. Min Act: -0.0000

Data Index: 752931 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1901404 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2062. Min Act: -0.0000

Data Index: 1579829 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2796. Min Act: -0.0000

Data Index: 997398 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1697050 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2694. Min Act: -0.0000

Data Index: 220923 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.3277. Min Act: -0.0000

Data Index: 800956 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2372. Min Act: -0.0000

Data Index: 317642 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1705. Min Act: -0.0000

Data Index: 1598390 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2886. Min Act: -0.0000

Data Index: 730017 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1561141 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1503571 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1588120 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1875010 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 1.7752. Min Range: -1.7752

Max Act: 1.1106. Min Act: -0.0000

Data Index: 886245 (The Pile)

Max Activating Token Index: 876