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

Dataset: The Pile

Neuron 957 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.6453. Min Act: -0.0000

Data Index: 1164947 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3543. Min Act: -0.0000

Data Index: 354862 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.4039. Min Act: -0.0000

Data Index: 901703 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.4041. Min Act: -0.0000

Data Index: 297916 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1669261 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1982656 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1240958 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.4921. Min Act: -0.0000

Data Index: 517037 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1217236 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1801986 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1243753 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1917817 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3571. Min Act: -0.0000

Data Index: 435703 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1403332 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3754. Min Act: -0.0000

Data Index: 670239 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3642. Min Act: -0.0000

Data Index: 481792 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1506330 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.2334. Min Act: -0.0000

Data Index: 805907 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1904426 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 1.6453. Min Range: -1.6453

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1343031 (The Pile)

Max Activating Token Index: 1000