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

Dataset: The Pile

Neuron 4143 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: 1.9502. Min Range: -1.9502

Max Act: 1.9502. Min Act: -0.0000

Data Index: 1122679 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.8864. Min Act: -0.0000

Data Index: 276609 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.7812. Min Act: -0.0000

Data Index: 1174272 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1564087 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6756. Min Act: -0.0000

Data Index: 227691 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1710602 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6885. Min Act: -0.0000

Data Index: 498047 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1632610 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.6282. Min Act: -0.0000

Data Index: 1077775 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4385. Min Act: -0.0000

Data Index: 275728 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4149. Min Act: -0.0000

Data Index: 117789 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1943939 (The Pile)

Max Activating Token Index: 75

Text #12

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1766815 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5655. Min Act: -0.0000

Data Index: 558510 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5667. Min Act: -0.0000

Data Index: 402861 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5811. Min Act: -0.0000

Data Index: 447755 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5423. Min Act: -0.0000

Data Index: 431395 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5369. Min Act: -0.0000

Data Index: 1102227 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.4804. Min Act: -0.0000

Data Index: 1920693 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 1.9502. Min Range: -1.9502

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1802824 (The Pile)

Max Activating Token Index: 666