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

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

Neuron 2034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1550303 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1559417 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1638227 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1445801 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1654749 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1396237 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1587556 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1639159 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1600614 (Python Code)

Max Activating Token Index: 765

Text #9

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1465760 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1431915 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1376402 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1396498 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1551484 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1468221 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1448571 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1472654 (Python Code)

Max Activating Token Index: 308

Text #17

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1360871 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1398848 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.8229. Min Range: -0.8229

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1488235 (Python Code)

Max Activating Token Index: 313