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

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

Neuron 3900 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1573114 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1573857 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4549. Min Act: -0.0000

Data Index: 781320 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3917. Min Act: -0.0000

Data Index: 632894 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1582832 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1372634 (Python Code)

Max Activating Token Index: 869

Text #6

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.5157. Min Act: -0.0000

Data Index: 689899 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1196659 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1633022 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1412007 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1302531 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1390970 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1532629 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1506748 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1629143 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1461966 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1454050 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1597060 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1278895 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.5372. Min Range: -0.5372

Max Act: 0.3761. Min Act: -0.0000

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 442