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

Dataset: The Pile

Neuron 87 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: 0.4978. Min Range: -0.4978

Max Act: 0.4830. Min Act: -0.0000

Data Index: 825505 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1760406 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1105587 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4058. Min Act: -0.0000

Data Index: 802073 (The Pile)

Max Activating Token Index: 741

Text #4

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1323107 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1244911 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3768. Min Act: -0.0000

Data Index: 321322 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3952. Min Act: -0.0000

Data Index: 336361 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1536315 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3739. Min Act: -0.0000

Data Index: 893369 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1437246 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3860. Min Act: -0.0000

Data Index: 137086 (The Pile)

Max Activating Token Index: 728

Text #12

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1491852 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1801748 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3958. Min Act: -0.0000

Data Index: 367051 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3668. Min Act: -0.0000

Data Index: 67697 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1874865 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1686668 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3583. Min Act: -0.0000

Data Index: 945452 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.4978. Min Range: -0.4978

Max Act: 0.3681. Min Act: -0.0000

Data Index: 84409 (The Pile)

Max Activating Token Index: 827