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

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

Neuron 4244 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.9683. Min Act: -0.0000

Data Index: 399863 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.6838. Min Act: -0.0000

Data Index: 1352912 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.5424. Min Act: -0.0000

Data Index: 638248 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.3377. Min Act: -0.0000

Data Index: 207858 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.4181. Min Act: -0.0000

Data Index: 952530 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1233229 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1144627 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2721. Min Act: -0.0000

Data Index: 83433 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2652. Min Act: -0.0000

Data Index: 253175 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1770. Min Act: -0.0000

Data Index: 494208 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2221. Min Act: -0.0000

Data Index: 888403 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.2702. Min Act: -0.0000

Data Index: 532580 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1162509 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1615. Min Act: -0.0000

Data Index: 183455 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0753. Min Act: -0.0000

Data Index: 719308 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1409. Min Act: -0.0000

Data Index: 897769 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1184. Min Act: -0.0000

Data Index: 251335 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0884. Min Act: -0.0000

Data Index: 291894 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.1461. Min Act: -0.0000

Data Index: 703406 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 1.9683. Min Range: -1.9683

Max Act: 1.0799. Min Act: -0.0000

Data Index: 129006 (C4 (Web Text))

Max Activating Token Index: 443