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

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

Neuron 800 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.6868. Min Act: -0.0000

Data Index: 654479 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 2.6868. Min Range: -2.6868

Max Act: 2.5612. Min Act: -0.0000

Data Index: 532539 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.9797. Min Act: -0.0000

Data Index: 251107 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.7375. Min Act: -0.0000

Data Index: 267819 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.6420. Min Act: -0.0000

Data Index: 359757 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.7064. Min Act: 0.0000

Data Index: 753049 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.4625. Min Act: -0.0000

Data Index: 563808 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.2814. Min Act: -0.0000

Data Index: 408641 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.3604. Min Act: -0.0000

Data Index: 212392 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.2360. Min Act: -0.0000

Data Index: 331539 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1103386 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1514225 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1607873 (Python Code)

Max Activating Token Index: 825

Text #13

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.1858. Min Act: -0.0000

Data Index: 606333 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1646115 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1620052 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.1336. Min Act: -0.0000

Data Index: 1150387 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1491741 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.1356. Min Act: -0.0000

Data Index: 517318 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 2.6868. Min Range: -2.6868

Max Act: 1.0649. Min Act: -0.0000

Data Index: 182314 (C4 (Web Text))

Max Activating Token Index: 796