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

Dataset: The Pile

Neuron 3288 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: 0.4876. Min Range: -0.4876

Max Act: 0.4736. Min Act: -0.0000

Data Index: 777123 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4767. Min Act: -0.0000

Data Index: 393753 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4876. Min Act: -0.0000

Data Index: 126700 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1228024 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1559447 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4426. Min Act: -0.0000

Data Index: 358483 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1637327 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4164. Min Act: -0.0000

Data Index: 510156 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1644903 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1691692 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1928108 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4305. Min Act: -0.0000

Data Index: 527769 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1151727 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3664. Min Act: -0.0000

Data Index: 752953 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1080864 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4001. Min Act: -0.0000

Data Index: 400340 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3951. Min Act: -0.0000

Data Index: 849267 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4035. Min Act: -0.0000

Data Index: 544023 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3804. Min Act: -0.0000

Data Index: 630267 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3535. Min Act: -0.0000

Data Index: 317651 (The Pile)

Max Activating Token Index: 866