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

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

Neuron 1818 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9860. Min Act: -0.0001

Data Index: 1656607 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1444198 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1461671 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9000. Min Act: -0.0001

Data Index: 1608558 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1430488 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9284. Min Act: -0.0001

Data Index: 1560064 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8654. Min Act: -0.0001

Data Index: 1465099 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9252. Min Act: -0.0001

Data Index: 1462130 (Python Code)

Max Activating Token Index: 352

Text #8

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1399157 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8373. Min Act: -0.0001

Data Index: 1442853 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8980. Min Act: -0.0001

Data Index: 1535252 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8677. Min Act: -0.0001

Data Index: 1645736 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8464. Min Act: -0.0001

Data Index: 1490898 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1392192 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8836. Min Act: -0.0001

Data Index: 1411630 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1535028 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8982. Min Act: -0.0001

Data Index: 230180 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8731. Min Act: -0.0001

Data Index: 1412436 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1434965 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1612339 (Python Code)

Max Activating Token Index: 211