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

Dataset: The Pile

Neuron 229 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.9370. Min Act: -0.0000

Data Index: 780250 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1991644 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.7335. Min Act: -0.0000

Data Index: 191484 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.7057. Min Act: -0.0000

Data Index: 548936 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5943. Min Act: -0.0000

Data Index: 577847 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1650059 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.6080. Min Act: 0.0000

Data Index: 646935 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1759090 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1395847 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1233737 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1316720 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5013. Min Act: -0.0000

Data Index: 443910 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5200. Min Act: 0.0000

Data Index: 1063513 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1065890 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4808. Min Act: 0.0000

Data Index: 1350237 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4890. Min Act: -0.0000

Data Index: 282772 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.5083. Min Act: -0.0000

Data Index: 660085 (The Pile)

Max Activating Token Index: 289

Text #17

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4873. Min Act: -0.0000

Data Index: 197806 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1443655 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.9370. Min Range: -0.9370

Max Act: 0.4778. Min Act: -0.0000

Data Index: 145898 (The Pile)

Max Activating Token Index: 834