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

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

Neuron 780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1466364 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8535. Min Act: -0.0000

Data Index: 953143 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1367626 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8279. Min Act: -0.0000

Data Index: 224631 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1189199 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8671. Min Act: -0.0000

Data Index: 72712 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8482. Min Act: -0.0000

Data Index: 711850 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.8790. Min Act: -0.0000

Data Index: 318817 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7478. Min Act: -0.0000

Data Index: 43166 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1338178 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7530. Min Act: -0.0000

Data Index: 381988 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7427. Min Act: -0.0000

Data Index: 620714 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1404375 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1263875 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7658. Min Act: -0.0000

Data Index: 104213 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7588. Min Act: -0.0000

Data Index: 484676 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1582879 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1202603 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.9660. Min Range: -0.9660

Max Act: 0.6636. Min Act: -0.0000

Data Index: 105759 (C4 (Web Text))

Max Activating Token Index: 978