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

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

Neuron 2540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0002

Data Index: 976824 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1326819 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0700. Min Act: -0.0002

Data Index: 150853 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1143899 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0632. Min Act: -0.0002

Data Index: 674574 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0649. Min Act: -0.0002

Data Index: 540775 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1287773 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0609. Min Act: -0.0002

Data Index: 756539 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0551. Min Act: -0.0002

Data Index: 4419 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0624. Min Act: -0.0002

Data Index: 392608 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0561. Min Act: -0.0002

Data Index: 272709 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0583. Min Act: -0.0002

Data Index: 707674 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0599. Min Act: -0.0002

Data Index: 248207 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0620. Min Act: -0.0002

Data Index: 144755 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1258258 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0608. Min Act: -0.0002

Data Index: 908016 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0563. Min Act: -0.0002

Data Index: 644272 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0501. Min Act: -0.0002

Data Index: 253185 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0534. Min Act: -0.0002

Data Index: 860714 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0551. Min Act: -0.0002

Data Index: 987368 (C4 (Web Text))

Max Activating Token Index: 620