Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1067. Min Act: -0.0000

Data Index: 923221 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1012. Min Act: -0.0000

Data Index: 108387 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0995. Min Act: -0.0001

Data Index: 759473 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1023. Min Act: -0.0000

Data Index: 60235 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0857. Min Act: -0.0000

Data Index: 166664 (The Pile)

Max Activating Token Index: 715

Text #5

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0893. Min Act: -0.0000

Data Index: 193246 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0856. Min Act: -0.0000

Data Index: 681773 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1151008 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1313717 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1081022 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1391673 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0744. Min Act: -0.0000

Data Index: 512737 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0773. Min Act: -0.0001

Data Index: 576493 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0797. Min Act: -0.0000

Data Index: 314027 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0766. Min Act: -0.0000

Data Index: 252709 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1084446 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1278096 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0701. Min Act: -0.0000

Data Index: 127298 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0731. Min Act: -0.0000

Data Index: 180437 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0773. Min Act: -0.0000

Data Index: 641950 (The Pile)

Max Activating Token Index: 688