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

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

Neuron 1384 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0002

Data Index: 617918 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1336459 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1311972 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1102. Min Act: -0.0002

Data Index: 645813 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1023. Min Act: -0.0002

Data Index: 513107 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0949. Min Act: -0.0002

Data Index: 361596 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0987. Min Act: -0.0002

Data Index: 11664 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0946. Min Act: -0.0002

Data Index: 657127 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0918. Min Act: -0.0002

Data Index: 474802 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0880. Min Act: -0.0002

Data Index: 153837 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0855. Min Act: -0.0002

Data Index: 970273 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0807. Min Act: -0.0002

Data Index: 241468 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0808. Min Act: -0.0003

Data Index: 709320 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0867. Min Act: -0.0002

Data Index: 577484 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0836. Min Act: -0.0002

Data Index: 187683 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0790. Min Act: -0.0002

Data Index: 344495 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0711. Min Act: -0.0002

Data Index: 862543 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0767. Min Act: -0.0002

Data Index: 399059 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0739. Min Act: -0.0002

Data Index: 464220 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1233476 (C4 (Web Text))

Max Activating Token Index: 293