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

Dataset: The Pile

Neuron 968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2718. Min Act: -0.0000

Data Index: 296827 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0186. Min Act: -0.0000

Data Index: 1480557 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0262. Min Act: -0.0000

Data Index: 953393 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1923402 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9059. Min Act: -0.0000

Data Index: 259527 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1665505 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1955358 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1034461 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1459953 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1535323 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8156. Min Act: -0.0000

Data Index: 168340 (The Pile)

Max Activating Token Index: 605

Text #11

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8415. Min Act: -0.0000

Data Index: 739679 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7641. Min Act: -0.0000

Data Index: 792330 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1797451 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1851952 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1885860 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8048. Min Act: -0.0000

Data Index: 811954 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8145. Min Act: -0.0000

Data Index: 984831 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7103. Min Act: -0.0000

Data Index: 496103 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.7686. Min Act: -0.0000

Data Index: 754197 (The Pile)

Max Activating Token Index: 232