Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1873. Min Act: -0.0001

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1602. Min Act: -0.0001

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1609. Min Act: -0.0001

Data Index: 317511 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1588. Min Act: -0.0001

Data Index: 131756 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1750. Min Act: -0.0001

Data Index: 336457 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1759. Min Act: -0.0001

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1713. Min Act: -0.0001

Data Index: 918094 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0001

Data Index: 525759 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1782. Min Act: -0.0001

Data Index: 194847 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1271721 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1762. Min Act: -0.0001

Data Index: 149429 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1212526 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1615. Min Act: -0.0001

Data Index: 868918 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1560. Min Act: -0.0001

Data Index: 573889 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1603. Min Act: -0.0001

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1736. Min Act: -0.0001

Data Index: 58741 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1687. Min Act: -0.0001

Data Index: 263667 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1683. Min Act: -0.0001

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1504. Min Act: -0.0001

Data Index: 24361 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1670. Min Act: -0.0001

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 764