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

Dataset: The Pile

Neuron 1962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1237401 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5626. Min Act: -0.0000

Data Index: 91688 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1955395 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4769. Min Act: -0.0000

Data Index: 951583 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1304489 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1700651 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4929. Min Act: -0.0000

Data Index: 384599 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1204422 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1482495 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4210. Min Act: -0.0000

Data Index: 175993 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1883899 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1143081 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4688. Min Act: -0.0000

Data Index: 769455 (The Pile)

Max Activating Token Index: 892

Text #13

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1479788 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4684. Min Act: -0.0000

Data Index: 645002 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4170. Min Act: -0.0000

Data Index: 518063 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4781. Min Act: -0.0000

Data Index: 979606 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1918246 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1478206 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3731. Min Act: -0.0000

Data Index: 331420 (The Pile)

Max Activating Token Index: 560