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

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

Neuron 4346 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1510501 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1577392 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1544544 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1465138 (Python Code)

Max Activating Token Index: 293

Text #4

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1346662 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1488590 (Python Code)

Max Activating Token Index: 498

Text #6

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1423123 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1586592 (Python Code)

Max Activating Token Index: 848

Text #8

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.8275. Min Act: -0.0001

Data Index: 915259 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1449288 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1024264 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7667. Min Act: -0.0001

Data Index: 1184813 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6028. Min Act: -0.0001

Data Index: 217731 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7002. Min Act: -0.0001

Data Index: 602343 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7638. Min Act: -0.0000

Data Index: 766588 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6639. Min Act: -0.0001

Data Index: 196377 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.7056. Min Act: -0.0001

Data Index: 914779 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6746. Min Act: -0.0001

Data Index: 4279 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1471457 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 0.9744. Min Range: -0.9744

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1641829 (Python Code)

Max Activating Token Index: 504