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

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

Neuron 753 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0665. Min Act: -0.0001

Data Index: 728123 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1205109 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1346937 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0693. Min Act: -0.0001

Data Index: 906099 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0001

Data Index: 74208 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1336063 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0621. Min Act: -0.0001

Data Index: 460725 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1267950 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0579. Min Act: -0.0001

Data Index: 773491 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1014551 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0574. Min Act: -0.0001

Data Index: 323252 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1032192 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0574. Min Act: -0.0001

Data Index: 160767 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1322332 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0578. Min Act: -0.0001

Data Index: 601284 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0601. Min Act: -0.0001

Data Index: 601403 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0586. Min Act: -0.0001

Data Index: 975953 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0562. Min Act: -0.0001

Data Index: 237133 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1001748 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0621. Min Act: -0.0001

Data Index: 405367 (C4 (Web Text))

Max Activating Token Index: 282