Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.9878. Min Act: -0.0001

Data Index: 851239 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.9686. Min Act: -0.0001

Data Index: 83235 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8640. Min Act: -0.0001

Data Index: 704648 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.9131. Min Act: -0.0001

Data Index: 586204 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.9620. Min Act: -0.0001

Data Index: 17747 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8872. Min Act: -0.0001

Data Index: 250599 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.9001. Min Act: -0.0001

Data Index: 457273 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8874. Min Act: -0.0001

Data Index: 1150013 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8975. Min Act: -0.0001

Data Index: 943602 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8887. Min Act: -0.0001

Data Index: 208052 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8809. Min Act: -0.0001

Data Index: 1222467 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8099. Min Act: -0.0001

Data Index: 110368 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8265. Min Act: -0.0001

Data Index: 431526 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8708. Min Act: -0.0001

Data Index: 982992 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1275272 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8057. Min Act: -0.0001

Data Index: 614461 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1290757 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8076. Min Act: -0.0001

Data Index: 1081948 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1037555 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.9878. Min Range: -0.9878

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1246748 (C4 (Web Text))

Max Activating Token Index: 160