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

Dataset: The Pile

Neuron 4559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1057926 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9349. Min Act: -0.0000

Data Index: 683530 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1680495 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1612292 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1238109 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9023. Min Act: -0.0000

Data Index: 946509 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8934. Min Act: -0.0000

Data Index: 777959 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8249. Min Act: -0.0000

Data Index: 751073 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1440286 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7914. Min Act: -0.0000

Data Index: 719161 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1690648 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8146. Min Act: -0.0000

Data Index: 379244 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7939. Min Act: -0.0000

Data Index: 876112 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1723502 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7960. Min Act: -0.0000

Data Index: 119080 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7428. Min Act: -0.0000

Data Index: 197805 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7633. Min Act: -0.0000

Data Index: 215623 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1548030 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7825. Min Act: -0.0000

Data Index: 547437 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1716642 (The Pile)

Max Activating Token Index: 189