Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1378889 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1374424 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1405285 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1546777 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1622930 (Python Code)

Max Activating Token Index: 229

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1656868 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0304. Min Act: -0.0002

Data Index: 427151 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1635752 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1477902 (Python Code)

Max Activating Token Index: 866

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1571072 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1613375 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1490586 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1366450 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1528010 (Python Code)

Max Activating Token Index: 554

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1458650 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1597801 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1312954 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1615035 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1458573 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1591524 (Python Code)

Max Activating Token Index: 295