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

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

Neuron 1932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.7562. Min Act: -0.0000

Data Index: 953000 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1298903 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.6690. Min Act: -0.0000

Data Index: 258706 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1232345 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5846. Min Act: -0.0000

Data Index: 635129 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5741. Min Act: -0.0000

Data Index: 327962 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5530. Min Act: -0.0000

Data Index: 380974 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5508. Min Act: -0.0000

Data Index: 647679 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5399. Min Act: -0.0000

Data Index: 743297 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5555. Min Act: -0.0000

Data Index: 787941 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5750. Min Act: -0.0000

Data Index: 976812 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5166. Min Act: -0.0000

Data Index: 876499 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5508. Min Act: -0.0000

Data Index: 497678 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.4955. Min Act: -0.0000

Data Index: 731303 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1247733 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5195. Min Act: -0.0000

Data Index: 303425 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5134. Min Act: -0.0000

Data Index: 440468 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5284. Min Act: -0.0000

Data Index: 97138 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1349444 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.7562. Min Range: -0.7562

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1285978 (C4 (Web Text))

Max Activating Token Index: 51