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

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

Neuron 720 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1852. Min Act: -0.0001

Data Index: 18637 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1901. Min Act: -0.0001

Data Index: 646749 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1914. Min Act: -0.0001

Data Index: 485028 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1679. Min Act: -0.0001

Data Index: 125538 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1257879 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1686. Min Act: -0.0001

Data Index: 777655 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1704. Min Act: -0.0001

Data Index: 817259 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1349507 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1609. Min Act: -0.0001

Data Index: 73175 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1640. Min Act: -0.0001

Data Index: 619631 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1537. Min Act: -0.0001

Data Index: 800988 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1584. Min Act: -0.0001

Data Index: 14006 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1628. Min Act: -0.0001

Data Index: 859843 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1077676 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1617. Min Act: -0.0001

Data Index: 519942 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1599. Min Act: -0.0001

Data Index: 217227 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1595. Min Act: -0.0001

Data Index: 812175 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1591. Min Act: -0.0001

Data Index: 726377 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1535. Min Act: -0.0001

Data Index: 286920 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.1914. Min Range: -0.1914

Max Act: 0.1647. Min Act: -0.0001

Data Index: 296128 (C4 (Web Text))

Max Activating Token Index: 691