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

Dataset: The Pile

Neuron 4019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9410. Min Act: -0.0000

Data Index: 686602 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1077532 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8803. Min Act: -0.0000

Data Index: 166807 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1790260 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9584. Min Act: -0.0000

Data Index: 145391 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1772887 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1766477 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8429. Min Act: -0.0000

Data Index: 341185 (The Pile)

Max Activating Token Index: 568

Text #8

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7906. Min Act: -0.0000

Data Index: 843264 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 1.0608. Min Range: -1.0608

Max Act: 1.0608. Min Act: -0.0000

Data Index: 323431 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1313281 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1892431 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1755174 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6560. Min Act: -0.0000

Data Index: 92922 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6905. Min Act: -0.0000

Data Index: 918677 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7277. Min Act: -0.0000

Data Index: 613568 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7035. Min Act: -0.0000

Data Index: 648661 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1846030 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1368131 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1614987 (The Pile)

Max Activating Token Index: 940