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

Dataset: The Pile

Neuron 1150 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: 0.5711. Min Range: -0.5711

Max Act: 0.5478. Min Act: -0.0000

Data Index: 752198 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5639. Min Act: 0.0000

Data Index: 1844747 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5709. Min Act: 0.0000

Data Index: 208597 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5711. Min Act: -0.0000

Data Index: 909270 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5215. Min Act: -0.0000

Data Index: 618917 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1542939 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5628. Min Act: -0.0000

Data Index: 197936 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1081138 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1278741 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.5216. Min Act: -0.0000

Data Index: 461097 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1393012 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1835570 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4764. Min Act: -0.0000

Data Index: 578341 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4574. Min Act: 0.0000

Data Index: 1511137 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1022148 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1704931 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4666. Min Act: -0.0000

Data Index: 376906 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4924. Min Act: -0.0000

Data Index: 921518 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4917. Min Act: 0.0000

Data Index: 1554288 (The Pile)

Max Activating Token Index: 238

Text #19

Max Range: 0.5711. Min Range: -0.5711

Max Act: 0.4552. Min Act: -0.0000

Data Index: 652991 (The Pile)

Max Activating Token Index: 50