Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1497237 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1490547 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0959. Min Act: -0.0001

Data Index: 25302 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1550323 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1122549 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0803. Min Act: -0.0001

Data Index: 948598 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1548280 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1580851 (Python Code)

Max Activating Token Index: 772

Text #8

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1460067 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0785. Min Act: -0.0001

Data Index: 475462 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1442237 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0791. Min Act: -0.0001

Data Index: 891226 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0758. Min Act: -0.0001

Data Index: 386417 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0746. Min Act: -0.0001

Data Index: 856979 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0735. Min Act: -0.0001

Data Index: 425575 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0761. Min Act: -0.0001

Data Index: 27831 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1404649 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0752. Min Act: -0.0001

Data Index: 963897 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1437848 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0777. Min Act: -0.0001

Data Index: 635825 (C4 (Web Text))

Max Activating Token Index: 65