Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7648. Min Act: -0.0000

Data Index: 9746 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1929276 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7417. Min Act: -0.0000

Data Index: 696062 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1691465 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6987. Min Act: -0.0000

Data Index: 145890 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1956601 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1283406 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6724. Min Act: -0.0000

Data Index: 245354 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6916. Min Act: -0.0000

Data Index: 858698 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6912. Min Act: -0.0000

Data Index: 955586 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6747. Min Act: -0.0000

Data Index: 762213 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1835893 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6887. Min Act: -0.0000

Data Index: 785402 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6783. Min Act: -0.0000

Data Index: 622853 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6870. Min Act: -0.0000

Data Index: 393130 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6608. Min Act: -0.0000

Data Index: 564087 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1871908 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1848569 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1983834 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6661. Min Act: -0.0000

Data Index: 596550 (The Pile)

Max Activating Token Index: 391