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

Dataset: The Pile

Neuron 523 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0555. Min Range: -3.0555

Max Act: 3.0555. Min Act: -0.0000

Data Index: 1597610 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.7284. Min Act: -0.0000

Data Index: 984309 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1344418 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.3801. Min Act: -0.0000

Data Index: 524835 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.0005. Min Act: -0.0000

Data Index: 196160 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.0098. Min Act: -0.0000

Data Index: 183264 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1897226 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.3044. Min Act: -0.0000

Data Index: 1208367 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.4660. Min Act: -0.0000

Data Index: 1653669 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.9103. Min Act: -0.0000

Data Index: 1585192 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1051267 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1011312 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1368705 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.7490. Min Act: -0.0000

Data Index: 117199 (The Pile)

Max Activating Token Index: 799

Text #14

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.3631. Min Act: -0.0000

Data Index: 1000540 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.9387. Min Act: -0.0000

Data Index: 1962520 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.9828. Min Act: -0.0000

Data Index: 1799441 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.0451. Min Act: -0.0000

Data Index: 39223 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 3.0555. Min Range: -3.0555

Max Act: 2.0424. Min Act: -0.0000

Data Index: 595654 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 3.0555. Min Range: -3.0555

Max Act: 1.9307. Min Act: -0.0000

Data Index: 650035 (The Pile)

Max Activating Token Index: 352