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

Dataset: The Pile

Neuron 3119 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: 0.9606. Min Range: -0.9606

Max Act: 0.9606. Min Act: 0.0000

Data Index: 487156 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.9285. Min Act: -0.0000

Data Index: 980808 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6993. Min Act: 0.0000

Data Index: 812894 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6976. Min Act: -0.0000

Data Index: 393541 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1396265 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6101. Min Act: -0.0000

Data Index: 398704 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1396449 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1304863 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5413. Min Act: -0.0000

Data Index: 273341 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1346829 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1118722 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1599818 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1988155 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1982490 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5040. Min Act: -0.0000

Data Index: 957780 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4975. Min Act: -0.0000

Data Index: 3411 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4819. Min Act: -0.0000

Data Index: 851463 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.5127. Min Act: -0.0000

Data Index: 681991 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4774. Min Act: 0.0000

Data Index: 1026474 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.9606. Min Range: -0.9606

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1505808 (The Pile)

Max Activating Token Index: 710