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

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

Neuron 1431 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.6542. Min Act: -0.0000

Data Index: 321627 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.1888. Min Act: -0.0000

Data Index: 251678 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.1762. Min Act: -0.0000

Data Index: 831299 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.2645. Min Act: -0.0000

Data Index: 820629 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.9917. Min Act: -0.0000

Data Index: 487724 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.0362. Min Act: -0.0000

Data Index: 668613 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.9321. Min Act: 0.0000

Data Index: 918392 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.9124. Min Act: -0.0000

Data Index: 338934 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.0102. Min Act: -0.0000

Data Index: 475893 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.7933. Min Act: -0.0000

Data Index: 608817 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 2.6542. Min Range: -2.6542

Max Act: 2.1385. Min Act: -0.0000

Data Index: 207599 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.8311. Min Act: -0.0000

Data Index: 566717 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1096713 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.5939. Min Act: -0.0000

Data Index: 902674 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.8920. Min Act: -0.0000

Data Index: 567548 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.6287. Min Act: -0.0000

Data Index: 364299 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.8107. Min Act: -0.0000

Data Index: 690907 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1246553 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.7889. Min Act: -0.0000

Data Index: 355157 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 2.6542. Min Range: -2.6542

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1097796 (C4 (Web Text))

Max Activating Token Index: 5