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

Dataset: The Pile

Neuron 512 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: 0.9564. Min Range: -0.9564

Max Act: 0.9564. Min Act: -0.0000

Data Index: 734475 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.7096. Min Act: -0.0000

Data Index: 686872 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1774366 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1877811 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1065212 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1494199 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1652054 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5710. Min Act: -0.0000

Data Index: 207201 (The Pile)

Max Activating Token Index: 910

Text #8

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5467. Min Act: -0.0000

Data Index: 390859 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1291322 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5796. Min Act: -0.0000

Data Index: 210152 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5496. Min Act: -0.0000

Data Index: 812900 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5570. Min Act: -0.0000

Data Index: 815684 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5673. Min Act: -0.0000

Data Index: 1848241 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1299316 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5221. Min Act: -0.0000

Data Index: 782875 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4850. Min Act: -0.0000

Data Index: 827379 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1056247 (The Pile)

Max Activating Token Index: 529

Text #18

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.5005. Min Act: -0.0000

Data Index: 871471 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 0.9564. Min Range: -0.9564

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1054184 (The Pile)

Max Activating Token Index: 937