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

Dataset: The Pile

Neuron 2391 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: 3.7773. Min Range: -3.7773

Max Act: 3.7773. Min Act: -0.0000

Data Index: 1182486 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6764. Min Act: -0.0000

Data Index: 706801 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.6590. Min Act: -0.0000

Data Index: 1910571 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.7047. Min Act: -0.0000

Data Index: 358115 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.4432. Min Act: -0.0000

Data Index: 383659 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.4668. Min Act: -0.0000

Data Index: 1140477 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.1763. Min Act: -0.0000

Data Index: 671206 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.9720. Min Act: -0.0000

Data Index: 1997315 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.9538. Min Act: -0.0000

Data Index: 1065100 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.0624. Min Act: -0.0000

Data Index: 1025207 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.9353. Min Act: -0.0000

Data Index: 1918271 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.5951. Min Act: -0.0000

Data Index: 154401 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.8749. Min Act: -0.0000

Data Index: 555234 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.2487. Min Act: -0.0000

Data Index: 1199791 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.8330. Min Act: -0.0000

Data Index: 1134125 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1833444 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.7621. Min Act: -0.0000

Data Index: 1494781 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.7642. Min Act: -0.0000

Data Index: 832421 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 3.7773. Min Range: -3.7773

Max Act: 2.8955. Min Act: -0.0000

Data Index: 213816 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 3.7773. Min Range: -3.7773

Max Act: 3.0272. Min Act: -0.0000

Data Index: 1941743 (The Pile)

Max Activating Token Index: 275