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

Dataset: The Pile

Neuron 257 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: 0.5696. Min Range: -0.5696

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1717435 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0000

Data Index: 335851 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5294. Min Act: -0.0000

Data Index: 673337 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5153. Min Act: -0.0000

Data Index: 903048 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1870184 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5584. Min Act: -0.0000

Data Index: 482431 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5106. Min Act: -0.0000

Data Index: 202277 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5083. Min Act: -0.0000

Data Index: 582235 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1846747 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5014. Min Act: -0.0000

Data Index: 616778 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5142. Min Act: -0.0000

Data Index: 759674 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1664722 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1057830 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4807. Min Act: -0.0000

Data Index: 955489 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1575042 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4975. Min Act: -0.0000

Data Index: 61145 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4894. Min Act: -0.0000

Data Index: 563081 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4711. Min Act: -0.0000

Data Index: 232670 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1749889 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4434. Min Act: -0.0000

Data Index: 643914 (The Pile)

Max Activating Token Index: 870