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

Dataset: The Pile

Neuron 1660 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: 0.8474. Min Range: -0.8474

Max Act: 0.8253. Min Act: -0.0000

Data Index: 488625 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1055861 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7522. Min Act: -0.0000

Data Index: 889800 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7887. Min Act: -0.0000

Data Index: 149100 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7667. Min Act: -0.0000

Data Index: 644271 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8474. Min Act: -0.0000

Data Index: 832062 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7462. Min Act: -0.0000

Data Index: 642087 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.8145. Min Act: -0.0000

Data Index: 921090 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1624174 (The Pile)

Max Activating Token Index: 394

Text #9

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7394. Min Act: -0.0000

Data Index: 339368 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7581. Min Act: -0.0000

Data Index: 471782 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1383865 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1677448 (The Pile)

Max Activating Token Index: 43

Text #13

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1346957 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7540. Min Act: -0.0000

Data Index: 14765 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1193711 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1222850 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1008021 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1026607 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 0.8474. Min Range: -0.8474

Max Act: 0.7113. Min Act: -0.0000

Data Index: 11277 (The Pile)

Max Activating Token Index: 690