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

Dataset: The Pile

Neuron 1952 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9729. Min Act: -0.0000

Data Index: 927643 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9377. Min Act: -0.0000

Data Index: 723724 (The Pile)

Max Activating Token Index: 403

Text #2

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1148479 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1893044 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1775139 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7795. Min Act: -0.0000

Data Index: 944777 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1517196 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7750. Min Act: -0.0000

Data Index: 419225 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7667. Min Act: -0.0000

Data Index: 454044 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6930. Min Act: -0.0000

Data Index: 848439 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1553700 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1966410 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7078. Min Act: -0.0000

Data Index: 942086 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1162033 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7079. Min Act: -0.0000

Data Index: 20110 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1861156 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7588. Min Act: -0.0000

Data Index: 163802 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1921741 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1531746 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1763459 (The Pile)

Max Activating Token Index: 806