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

Dataset: The Pile

Neuron 4837 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: 0.6824. Min Range: -0.6824

Max Act: 0.6814. Min Act: -0.0000

Data Index: 189294 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1495943 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1787168 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.6050. Min Act: -0.0000

Data Index: 222858 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1223114 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1349513 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1131527 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5083. Min Act: -0.0000

Data Index: 160482 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1079801 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1134168 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4975. Min Act: -0.0000

Data Index: 585530 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1693430 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4813. Min Act: -0.0000

Data Index: 435192 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1176288 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1159691 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1952742 (The Pile)

Max Activating Token Index: 422

Text #16

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1416346 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1935412 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1906026 (The Pile)

Max Activating Token Index: 830

Text #19

Max Range: 0.6824. Min Range: -0.6824

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1949519 (The Pile)

Max Activating Token Index: 977