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

Dataset: The Pile

Neuron 360 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: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1685122 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0834. Min Act: -0.0000

Data Index: 969379 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0847. Min Act: -0.0000

Data Index: 526187 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1910494 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1172445 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0742. Min Act: -0.0000

Data Index: 226337 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0789. Min Act: -0.0000

Data Index: 126237 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0700. Min Act: -0.0000

Data Index: 825983 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0730. Min Act: -0.0000

Data Index: 573143 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0818. Min Act: -0.0000

Data Index: 107526 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0686. Min Act: -0.0000

Data Index: 668007 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1135534 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0711. Min Act: -0.0000

Data Index: 594916 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0708. Min Act: -0.0000

Data Index: 244411 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1749190 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0574. Min Act: -0.0000

Data Index: 360391 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0673. Min Act: -0.0000

Data Index: 15119 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1075368 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1662982 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1097993 (The Pile)

Max Activating Token Index: 433