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

Dataset: The Pile

Neuron 275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1949966 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1153681 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6259. Min Act: -0.0000

Data Index: 850578 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4795. Min Act: -0.0000

Data Index: 550791 (The Pile)

Max Activating Token Index: 590

Text #4

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6400. Min Act: -0.0000

Data Index: 635037 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.6309. Min Act: -0.0000

Data Index: 1677655 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4591. Min Act: -0.0000

Data Index: 585029 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1001460 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5076. Min Act: -0.0000

Data Index: 921373 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4248. Min Act: -0.0000

Data Index: 944134 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1731058 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1434443 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1957142 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4717. Min Act: -0.0000

Data Index: 382472 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.3630. Min Act: -0.0000

Data Index: 273488 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1647917 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4419. Min Act: -0.0000

Data Index: 707318 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4267. Min Act: -0.0000

Data Index: 988862 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1476981 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 1.6788. Min Range: -1.6788

Max Act: 1.3344. Min Act: -0.0000

Data Index: 19642 (The Pile)

Max Activating Token Index: 416