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

Dataset: The Pile

Neuron 1218 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1479097 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.6928. Min Act: -0.0000

Data Index: 593130 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1271243 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1575660 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1593170 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1260. Min Act: -0.0000

Data Index: 359036 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1324897 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3042. Min Act: -0.0000

Data Index: 991335 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3887. Min Act: -0.0000

Data Index: 773072 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4417. Min Act: -0.0000

Data Index: 1576789 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1858958 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1445677 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3132. Min Act: -0.0000

Data Index: 220475 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1220530 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1965. Min Act: -0.0000

Data Index: 574972 (The Pile)

Max Activating Token Index: 360

Text #15

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1899. Min Act: -0.0000

Data Index: 30656 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3403. Min Act: -0.0000

Data Index: 674751 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1529325 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1074787 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 1.6928. Min Range: -1.6928

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1697545 (The Pile)

Max Activating Token Index: 818