Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.3012. Min Act: -0.0000

Data Index: 687874 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1212050 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1366. Min Act: -0.0000

Data Index: 587030 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1916. Min Act: -0.0000

Data Index: 50503 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1341830 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1178498 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2075. Min Act: -0.0000

Data Index: 1408092 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1988. Min Act: -0.0000

Data Index: 193192 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1696. Min Act: -0.0000

Data Index: 82547 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1411. Min Act: -0.0000

Data Index: 845813 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1543. Min Act: -0.0000

Data Index: 38487 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1185. Min Act: -0.0000

Data Index: 513741 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1620963 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1350. Min Act: -0.0000

Data Index: 663635 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0882. Min Act: -0.0000

Data Index: 206851 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.3012. Min Range: -1.3012

Max Act: 0.8888. Min Act: -0.0000

Data Index: 74937 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0505. Min Act: -0.0000

Data Index: 950641 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 1.3012. Min Range: -1.3012

Max Act: 0.9723. Min Act: -0.0000

Data Index: 823848 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0909. Min Act: -0.0000

Data Index: 639573 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1447360 (The Pile)

Max Activating Token Index: 703