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

Dataset: The Pile

Neuron 2003 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1933. Min Act: -0.0000

Data Index: 315541 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0723. Min Act: -0.0000

Data Index: 996099 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1216327 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0329. Min Act: -0.0000

Data Index: 1126334 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1072039 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0102. Min Act: -0.0000

Data Index: 821410 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0406. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1410. Min Act: -0.0000

Data Index: 203318 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1702960 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0238. Min Act: -0.0000

Data Index: 303353 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1063665 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8229. Min Act: -0.0000

Data Index: 514967 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1974251 (The Pile)

Max Activating Token Index: 332

Text #13

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9218. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8672. Min Act: -0.0000

Data Index: 385966 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1211738 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8501. Min Act: -0.0000

Data Index: 294950 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1891421 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0028. Min Act: -0.0000

Data Index: 726604 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.8173. Min Act: -0.0000

Data Index: 705268 (The Pile)

Max Activating Token Index: 657