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

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

Neuron 1077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1260709 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2768. Min Act: -0.0000

Data Index: 826570 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2384. Min Act: -0.0000

Data Index: 688064 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0979. Min Act: -0.0000

Data Index: 17666 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1077. Min Act: -0.0000

Data Index: 954530 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1481. Min Act: -0.0000

Data Index: 689322 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9796. Min Act: -0.0000

Data Index: 890880 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1128857 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9617. Min Act: -0.0000

Data Index: 28121 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0444. Min Act: -0.0000

Data Index: 565019 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1181689 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9543. Min Act: -0.0000

Data Index: 372552 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9982. Min Act: -0.0000

Data Index: 347378 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9951. Min Act: -0.0000

Data Index: 799290 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0147. Min Act: -0.0000

Data Index: 388906 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9271. Min Act: -0.0000

Data Index: 230534 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9560. Min Act: -0.0000

Data Index: 401806 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1279742 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9407. Min Act: -0.0000

Data Index: 191570 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1238003 (C4 (Web Text))

Max Activating Token Index: 944