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

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

Neuron 5556 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.8340. Min Act: -0.0000

Data Index: 677590 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7882. Min Act: -0.0000

Data Index: 188600 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7757. Min Act: -0.0000

Data Index: 984678 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5954. Min Act: -0.0000

Data Index: 864933 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1301806 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6726. Min Act: -0.0000

Data Index: 943766 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6284. Min Act: -0.0000

Data Index: 993010 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6930. Min Act: -0.0000

Data Index: 540601 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6146. Min Act: -0.0000

Data Index: 908027 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1126054 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5954. Min Act: -0.0000

Data Index: 661573 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5638. Min Act: -0.0000

Data Index: 773266 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1279298 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5889. Min Act: -0.0000

Data Index: 629886 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5746. Min Act: -0.0000

Data Index: 923806 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1285443 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1181279 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5642. Min Act: -0.0000

Data Index: 781972 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1114554 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.8340. Min Range: -0.8340

Max Act: 0.5938. Min Act: 0.0000

Data Index: 754013 (C4 (Web Text))

Max Activating Token Index: 72