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

Dataset: The Pile

Neuron 3797 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: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1924755 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1601937 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7987. Min Act: -0.0000

Data Index: 834867 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1920623 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7100. Min Act: -0.0000

Data Index: 526102 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7875. Min Act: -0.0000

Data Index: 505600 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7065. Min Act: -0.0000

Data Index: 512869 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1876923 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6739. Min Act: -0.0000

Data Index: 858926 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1298961 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6610. Min Act: -0.0000

Data Index: 357919 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6662. Min Act: -0.0000

Data Index: 274757 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6644. Min Act: -0.0000

Data Index: 768658 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6744. Min Act: -0.0000

Data Index: 900872 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1207113 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6559. Min Act: 0.0000

Data Index: 1301712 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6471. Min Act: -0.0000

Data Index: 695396 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6548. Min Act: -0.0000

Data Index: 796837 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6331. Min Act: -0.0000

Data Index: 207562 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6459. Min Act: -0.0000

Data Index: 771959 (The Pile)

Max Activating Token Index: 302