Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1041 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1650255 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1437640 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7528. Min Act: -0.0001

Data Index: 1362617 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7023. Min Act: -0.0001

Data Index: 1624282 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6898. Min Act: -0.0001

Data Index: 1448395 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7043. Min Act: -0.0001

Data Index: 1623399 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.7026. Min Act: -0.0001

Data Index: 1641381 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1538140 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1554984 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6296. Min Act: -0.0001

Data Index: 1491928 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6704. Min Act: -0.0001

Data Index: 1563129 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1408414 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1552736 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1592536 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5974. Min Act: -0.0001

Data Index: 1509445 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5996. Min Act: -0.0001

Data Index: 1632412 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1382413 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6109. Min Act: -0.0001

Data Index: 1510581 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5375. Min Act: -0.0001

Data Index: 1479710 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1595918 (Python Code)

Max Activating Token Index: 48