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

Dataset: The Pile

Neuron 955 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1303. Min Range: -1.1303

Max Act: 1.1303. Min Act: -0.0000

Data Index: 727769 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9666. Min Act: -0.0000

Data Index: 69201 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.9356. Min Act: -0.0000

Data Index: 989288 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1706163 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1734835 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1952725 (The Pile)

Max Activating Token Index: 711

Text #6

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7916. Min Act: -0.0000

Data Index: 623391 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1534145 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1471570 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1709641 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1843878 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8268. Min Act: -0.0000

Data Index: 905317 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.6779. Min Act: -0.0000

Data Index: 384223 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7692. Min Act: -0.0000

Data Index: 232750 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1470896 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.8094. Min Act: -0.0000

Data Index: 339415 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7034. Min Act: -0.0000

Data Index: 137159 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7006. Min Act: -0.0000

Data Index: 570782 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.6948. Min Act: -0.0000

Data Index: 233352 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.1303. Min Range: -1.1303

Max Act: 0.7274. Min Act: 0.0000

Data Index: 624821 (The Pile)

Max Activating Token Index: 501