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

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

Neuron 3447 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1381367 (Python Code)

Max Activating Token Index: 258

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6137. Min Act: -0.0001

Data Index: 1405248 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6371. Min Act: -0.0001

Data Index: 1416588 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6192. Min Act: -0.0001

Data Index: 1617420 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6152. Min Act: -0.0001

Data Index: 1363423 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1487944 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1463586 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5074. Min Act: -0.0001

Data Index: 1603136 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1522819 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5501. Min Act: -0.0001

Data Index: 1484707 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1609855 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1591786 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1540850 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5013. Min Act: -0.0001

Data Index: 1380804 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1431391 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1602212 (Python Code)

Max Activating Token Index: 647

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1419439 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1474696 (Python Code)

Max Activating Token Index: 357

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5018. Min Act: -0.0001

Data Index: 1557789 (Python Code)

Max Activating Token Index: 676

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1502856 (Python Code)

Max Activating Token Index: 416