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

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

Neuron 3898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5777. Min Act: -0.0001

Data Index: 940973 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5419. Min Act: -0.0001

Data Index: 792081 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5534. Min Act: -0.0001

Data Index: 984709 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5323. Min Act: -0.0001

Data Index: 635041 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5770. Min Act: -0.0001

Data Index: 755984 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5138. Min Act: -0.0001

Data Index: 959958 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4981. Min Act: -0.0001

Data Index: 149646 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5766. Min Act: -0.0001

Data Index: 1175032 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1326725 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.5370. Min Act: -0.0000

Data Index: 377804 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4846. Min Act: -0.0001

Data Index: 811464 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4748. Min Act: -0.0000

Data Index: 839168 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1323713 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4090. Min Act: -0.0001

Data Index: 742791 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.4004. Min Act: -0.0000

Data Index: 231524 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.3014. Min Act: -0.0001

Data Index: 435184 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.2731. Min Act: -0.0001

Data Index: 744208 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.2786. Min Act: -0.0001

Data Index: 137642 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.2598. Min Act: -0.0000

Data Index: 751515 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.5777. Min Range: -0.5777

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1512722 (Python Code)

Max Activating Token Index: 735