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

Dataset: The Pile

Neuron 1902 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: 0.5921. Min Range: -0.5921

Max Act: 0.5682. Min Act: -0.0000

Data Index: 260001 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1402561 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1973490 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5278. Min Act: -0.0000

Data Index: 635848 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5274. Min Act: -0.0000

Data Index: 345923 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5348. Min Act: -0.0000

Data Index: 877784 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5921. Min Act: -0.0000

Data Index: 781564 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5396. Min Act: -0.0000

Data Index: 928932 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4864. Min Act: -0.0000

Data Index: 133398 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1718222 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1889716 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1880250 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5023. Min Act: -0.0000

Data Index: 511583 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4743. Min Act: -0.0000

Data Index: 598231 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.5016. Min Act: -0.0000

Data Index: 780746 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4360. Min Act: -0.0000

Data Index: 298986 (The Pile)

Max Activating Token Index: 502

Text #16

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1364634 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4846. Min Act: -0.0000

Data Index: 407187 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1911472 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 0.5921. Min Range: -0.5921

Max Act: 0.4785. Min Act: -0.0000

Data Index: 963110 (The Pile)

Max Activating Token Index: 20