Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1899 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0470. Min Act: -0.0006

Data Index: 875385 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0006

Data Index: 26332 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0535. Min Act: -0.0006

Data Index: 1162964 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1262181 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0484. Min Act: -0.0006

Data Index: 981412 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1328701 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0521. Min Act: -0.0006

Data Index: 720392 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0506. Min Act: -0.0006

Data Index: 378197 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0474. Min Act: -0.0006

Data Index: 61652 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0535. Min Act: -0.0006

Data Index: 1020004 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0510. Min Act: -0.0006

Data Index: 584632 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0502. Min Act: -0.0006

Data Index: 699602 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0470. Min Act: -0.0006

Data Index: 72612 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0519. Min Act: -0.0006

Data Index: 906495 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1027567 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1092805 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0521. Min Act: -0.0006

Data Index: 937783 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0489. Min Act: -0.0006

Data Index: 673965 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0449. Min Act: -0.0006

Data Index: 322306 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0474. Min Act: -0.0006

Data Index: 631562 (C4 (Web Text))

Max Activating Token Index: 214