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

Dataset: The Pile

Neuron 2068 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: 3.1424. Min Range: -3.1424

Max Act: 3.1424. Min Act: -0.0000

Data Index: 336492 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 3.1424. Min Range: -3.1424

Max Act: 3.0529. Min Act: -0.0000

Data Index: 947593 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 3.1424. Min Range: -3.1424

Max Act: 2.5348. Min Act: -0.0000

Data Index: 755669 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 3.1424. Min Range: -3.1424

Max Act: 2.4215. Min Act: -0.0000

Data Index: 619555 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 3.1424. Min Range: -3.1424

Max Act: 2.1497. Min Act: -0.0000

Data Index: 362248 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1337821 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.8704. Min Act: -0.0000

Data Index: 620794 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.9962. Min Act: -0.0000

Data Index: 247550 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.9308. Min Act: -0.0000

Data Index: 1486894 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1974907 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.8813. Min Act: -0.0000

Data Index: 445816 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.7848. Min Act: -0.0000

Data Index: 413640 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.7251. Min Act: -0.0000

Data Index: 684661 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.7900. Min Act: -0.0000

Data Index: 566469 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1037233 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.6875. Min Act: -0.0000

Data Index: 702668 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.8043. Min Act: -0.0000

Data Index: 1620357 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.8060. Min Act: 0.0000

Data Index: 704079 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.6873. Min Act: -0.0000

Data Index: 303602 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 3.1424. Min Range: -3.1424

Max Act: 1.5710. Min Act: -0.0000

Data Index: 523417 (The Pile)

Max Activating Token Index: 803