Model: SoLU Model: 2 Layers, 2944 Neurons per Layer

Dataset: The Pile

Neuron 1477 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1482661 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1040494 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1652888 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0769. Min Act: -0.0002

Data Index: 559486 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0754. Min Act: -0.0002

Data Index: 116720 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1666486 (The Pile)

Max Activating Token Index: 198

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1664941 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0722. Min Act: -0.0001

Data Index: 495585 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0721. Min Act: -0.0002

Data Index: 686723 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1057900 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0686. Min Act: -0.0002

Data Index: 735862 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1893968 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0682. Min Act: -0.0002

Data Index: 425222 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0677. Min Act: -0.0002

Data Index: 631612 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1255112 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0695. Min Act: -0.0002

Data Index: 773712 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1139829 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0673. Min Act: -0.0002

Data Index: 181865 (The Pile)

Max Activating Token Index: 589

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0684. Min Act: -0.0002

Data Index: 351044 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1119746 (The Pile)

Max Activating Token Index: 437