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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3314 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3603. Min Act: -0.0000

Data Index: 193306 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3317. Min Act: -0.0000

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3177. Min Act: -0.0000

Data Index: 350010 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.3224. Min Act: -0.0000

Data Index: 792584 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2871. Min Act: -0.0000

Data Index: 773353 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2850. Min Act: -0.0000

Data Index: 508600 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.2741. Min Act: -0.0000

Data Index: 382192 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1943. Min Act: -0.0000

Data Index: 643075 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1982. Min Act: -0.0000

Data Index: 27618 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1742. Min Act: -0.0000

Data Index: 276479 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1625. Min Act: -0.0000

Data Index: 159636 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1699. Min Act: -0.0000

Data Index: 878692 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1807. Min Act: -0.0000

Data Index: 731519 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1746. Min Act: -0.0000

Data Index: 27416 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1803. Min Act: -0.0000

Data Index: 324111 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1965. Min Act: -0.0000

Data Index: 278451 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1751. Min Act: -0.0000

Data Index: 332892 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1128447 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1592. Min Act: -0.0000

Data Index: 904062 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3603. Min Range: -0.3603

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1150375 (C4 (Web Text))

Max Activating Token Index: 496