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

Dataset: The Pile

Neuron 2418 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: 5.8484. Min Range: -5.8484

Max Act: 5.8484. Min Act: -0.0000

Data Index: 1358991 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.3400. Min Act: -0.0000

Data Index: 319419 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.3240. Min Act: -0.0000

Data Index: 842571 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.2459. Min Act: -0.0000

Data Index: 1572079 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.3765. Min Act: -0.0000

Data Index: 1947872 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.8226. Min Act: -0.0000

Data Index: 669687 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.1863. Min Act: -0.0000

Data Index: 1082070 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 5.8484. Min Range: -5.8484

Max Act: 5.1400. Min Act: -0.0000

Data Index: 1827522 (The Pile)

Max Activating Token Index: 554

Text #8

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.9454. Min Act: -0.0000

Data Index: 1215668 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.7016. Min Act: -0.0000

Data Index: 1208031 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.8607. Min Act: -0.0000

Data Index: 293720 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.8639. Min Act: -0.0000

Data Index: 9084 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.2665. Min Act: -0.0000

Data Index: 1882661 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.5419. Min Act: -0.0000

Data Index: 213612 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.1961. Min Act: -0.0000

Data Index: 766191 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.1855. Min Act: -0.0000

Data Index: 64591 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 5.8484. Min Range: -5.8484

Max Act: 3.4963. Min Act: -0.0000

Data Index: 1216290 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.2959. Min Act: -0.0000

Data Index: 203469 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.1149. Min Act: -0.0000

Data Index: 1156913 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 5.8484. Min Range: -5.8484

Max Act: 4.4122. Min Act: -0.0000

Data Index: 679139 (The Pile)

Max Activating Token Index: 382