Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1511 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0865. Min Act: -0.0001

Data Index: 203628 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1481980 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1104639 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0759. Min Act: -0.0001

Data Index: 727107 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0777. Min Act: -0.0001

Data Index: 755779 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0753. Min Act: -0.0001

Data Index: 720353 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0784. Min Act: -0.0001

Data Index: 798796 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0786. Min Act: -0.0001

Data Index: 281720 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0682. Min Act: -0.0001

Data Index: 462978 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0728. Min Act: -0.0001

Data Index: 226654 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0734. Min Act: -0.0001

Data Index: 971494 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0755. Min Act: -0.0001

Data Index: 638789 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0768. Min Act: -0.0001

Data Index: 790327 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0679. Min Act: -0.0001

Data Index: 918133 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0616. Min Act: -0.0001

Data Index: 634097 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1115924 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1604306 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0689. Min Act: -0.0001

Data Index: 803892 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0717. Min Act: -0.0001

Data Index: 704248 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0879. Min Range: -0.0879

Max Act: 0.0646. Min Act: -0.0001

Data Index: 176269 (C4 (Web Text))

Max Activating Token Index: 975