Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1427 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1007711 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.3407. Min Act: -0.0001

Data Index: 721594 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1433795 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2901. Min Act: -0.0001

Data Index: 173603 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2801. Min Act: -0.0001

Data Index: 1349807 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2410. Min Act: -0.0001

Data Index: 529566 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1605057 (Python Code)

Max Activating Token Index: 930

Text #7

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2775. Min Act: -0.0001

Data Index: 1311454 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1623024 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1052760 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2696. Min Act: -0.0001

Data Index: 806215 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2530. Min Act: -0.0001

Data Index: 535003 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1626029 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2601. Min Act: -0.0001

Data Index: 391801 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2634. Min Act: -0.0001

Data Index: 591090 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2635. Min Act: -0.0001

Data Index: 634524 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1080490 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1289075 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2507. Min Act: -0.0001

Data Index: 262637 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.3758. Min Range: -0.3758

Max Act: 0.2648. Min Act: -0.0001

Data Index: 78876 (C4 (Web Text))

Max Activating Token Index: 741