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

Dataset: The Pile

Neuron 4390 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1399810 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1926822 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1542090 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5211. Min Act: -0.0000

Data Index: 625742 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1869479 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1515476 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1351408 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4921. Min Act: -0.0000

Data Index: 186052 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1546089 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1138391 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1474940 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1026230 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1608175 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4841. Min Act: -0.0000

Data Index: 659 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4387. Min Act: -0.0000

Data Index: 428879 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4499. Min Act: -0.0000

Data Index: 106174 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1752664 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4305. Min Act: -0.0000

Data Index: 55774 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1726816 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.5687. Min Range: -0.5687

Max Act: 0.4517. Min Act: -0.0000

Data Index: 405723 (The Pile)

Max Activating Token Index: 503