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

Dataset: The Pile

Neuron 1404 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: 3.1733. Min Range: -3.1733

Max Act: 3.1733. Min Act: -0.0000

Data Index: 1838293 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5967. Min Act: -0.0000

Data Index: 904160 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.8482. Min Act: -0.0000

Data Index: 1947712 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.6827. Min Act: -0.0000

Data Index: 510460 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1904276 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3563. Min Act: -0.0000

Data Index: 1272834 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4722. Min Act: -0.0000

Data Index: 252707 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3899. Min Act: -0.0000

Data Index: 1228186 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3877. Min Act: -0.0000

Data Index: 150296 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4807. Min Act: -0.0000

Data Index: 468357 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4808. Min Act: -0.0000

Data Index: 1493473 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1747053 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.4623. Min Act: -0.0000

Data Index: 796231 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.2325. Min Act: -0.0000

Data Index: 1411637 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.3046. Min Act: -0.0000

Data Index: 409044 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.0955. Min Act: -0.0000

Data Index: 561626 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.0474. Min Act: -0.0000

Data Index: 1295187 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.1221. Min Act: -0.0000

Data Index: 141405 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.0470. Min Act: -0.0000

Data Index: 1384805 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 3.1733. Min Range: -3.1733

Max Act: 2.2567. Min Act: -0.0000

Data Index: 562008 (The Pile)

Max Activating Token Index: 33