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

Dataset: The Pile

Neuron 4512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4815. Min Range: -3.4815

Max Act: 3.3572. Min Act: -0.0000

Data Index: 1644092 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 3.4815. Min Range: -3.4815

Max Act: 3.4815. Min Act: -0.0000

Data Index: 1934594 (The Pile)

Max Activating Token Index: 801

Text #2

Max Range: 3.4815. Min Range: -3.4815

Max Act: 3.4625. Min Act: -0.0000

Data Index: 547736 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.9565. Min Act: -0.0000

Data Index: 796800 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 3.4815. Min Range: -3.4815

Max Act: 3.2275. Min Act: -0.0000

Data Index: 1480222 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 3.4815. Min Range: -3.4815

Max Act: 3.0545. Min Act: -0.0000

Data Index: 1155328 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.9452. Min Act: -0.0000

Data Index: 873623 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.9567. Min Act: -0.0000

Data Index: 214746 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.9327. Min Act: -0.0000

Data Index: 1643781 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.8820. Min Act: -0.0000

Data Index: 1903872 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.8889. Min Act: -0.0000

Data Index: 824076 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.8778. Min Act: -0.0000

Data Index: 1149966 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.7617. Min Act: -0.0000

Data Index: 1152772 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.8496. Min Act: -0.0000

Data Index: 762657 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.8345. Min Act: -0.0000

Data Index: 1412863 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.6757. Min Act: -0.0000

Data Index: 842088 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.7869. Min Act: -0.0000

Data Index: 424278 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.7714. Min Act: -0.0000

Data Index: 993283 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.4770. Min Act: -0.0000

Data Index: 1237994 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 3.4815. Min Range: -3.4815

Max Act: 2.7248. Min Act: -0.0000

Data Index: 776032 (The Pile)

Max Activating Token Index: 715