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

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

Neuron 2283 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0001

Data Index: 710482 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0803. Min Act: -0.0001

Data Index: 839264 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1019927 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0657. Min Act: -0.0001

Data Index: 15447 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1341827 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1477574 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1588829 (Python Code)

Max Activating Token Index: 444

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0680. Min Act: -0.0001

Data Index: 276880 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0698. Min Act: -0.0000

Data Index: 789948 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1098551 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1248828 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1091591 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0679. Min Act: -0.0001

Data Index: 101229 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1114545 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1179435 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0611. Min Act: -0.0000

Data Index: 443837 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0561. Min Act: -0.0000

Data Index: 928836 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0679. Min Act: -0.0000

Data Index: 747920 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1387326 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0552. Min Act: -0.0001

Data Index: 302244 (C4 (Web Text))

Max Activating Token Index: 809