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

Dataset: The Pile

Neuron 3052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0901. Min Range: -1.0901

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1110110 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.9292. Min Act: 0.0000

Data Index: 388614 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1935496 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8211. Min Act: -0.0000

Data Index: 314170 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1285504 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1804441 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1867412 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7925. Min Act: -0.0000

Data Index: 248898 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8426. Min Act: -0.0000

Data Index: 429471 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8003. Min Act: -0.0000

Data Index: 710777 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8043. Min Act: -0.0000

Data Index: 261813 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1238731 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1859610 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1501256 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7525. Min Act: -0.0000

Data Index: 626634 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1205048 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1259444 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1329749 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1445450 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 1.0901. Min Range: -1.0901

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1190927 (The Pile)

Max Activating Token Index: 764