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

Dataset: The Pile

Neuron 1248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1840630 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1662437 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1965321 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1169876 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1038828 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7568. Min Act: -0.0000

Data Index: 903939 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8915. Min Act: -0.0000

Data Index: 1909909 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1244801 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8253. Min Act: -0.0000

Data Index: 310957 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8915. Min Act: -0.0000

Data Index: 925834 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1530761 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7837. Min Act: -0.0000

Data Index: 258160 (The Pile)

Max Activating Token Index: 880

Text #12

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1387090 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8228. Min Act: -0.0000

Data Index: 978125 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1017155 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8494. Min Act: -0.0000

Data Index: 816039 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1974856 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1105918 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1261969 (The Pile)

Max Activating Token Index: 202

Text #19

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8336. Min Act: -0.0000

Data Index: 228638 (The Pile)

Max Activating Token Index: 813