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

Dataset: The Pile

Neuron 814 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.7718. Min Act: -0.0000

Data Index: 79507 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6590. Min Act: -0.0000

Data Index: 208078 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1693990 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1105986 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1430915 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5764. Min Act: -0.0000

Data Index: 559542 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5705. Min Act: -0.0000

Data Index: 958713 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5735. Min Act: 0.0000

Data Index: 1828804 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5411. Min Act: -0.0000

Data Index: 580670 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5230. Min Act: -0.0000

Data Index: 345942 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1268568 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5776. Min Act: 0.0000

Data Index: 1732403 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1554124 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1516578 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5378. Min Act: -0.0000

Data Index: 344998 (The Pile)

Max Activating Token Index: 921

Text #15

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5197. Min Act: 0.0000

Data Index: 1795788 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5017. Min Act: -0.0000

Data Index: 45712 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.4852. Min Act: -0.0000

Data Index: 535424 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1739466 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.7718. Min Range: -0.7718

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1255144 (The Pile)

Max Activating Token Index: 150