Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3020 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1369748 (Python Code)

Max Activating Token Index: 449

Text #1

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.9413. Min Act: -0.0001

Data Index: 691716 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6307. Min Act: -0.0001

Data Index: 1496297 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6530. Min Act: -0.0001

Data Index: 654032 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1413418 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1622905 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6737. Min Act: -0.0001

Data Index: 386546 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1608874 (Python Code)

Max Activating Token Index: 418

Text #8

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1614807 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6294. Min Act: -0.0001

Data Index: 1386596 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6264. Min Act: -0.0001

Data Index: 1575534 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6242. Min Act: -0.0001

Data Index: 1503768 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6214. Min Act: -0.0001

Data Index: 1464539 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1516635 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6323. Min Act: -0.0001

Data Index: 1422139 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1484251 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1643623 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6024. Min Act: -0.0001

Data Index: 651814 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1638475 (Python Code)

Max Activating Token Index: 935

Text #19

Max Range: 0.9413. Min Range: -0.9413

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1560474 (Python Code)

Max Activating Token Index: 475