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

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

Neuron 25 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.4013. Min Act: -0.0000

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1496127 (Python Code)

Max Activating Token Index: 910

Text #2

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1850. Min Act: -0.0000

Data Index: 410185 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1512. Min Act: -0.0000

Data Index: 20694 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1394749 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1627133 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1461588 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1126246 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1576262 (Python Code)

Max Activating Token Index: 686

Text #9

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1260. Min Act: -0.0000

Data Index: 712966 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0926. Min Act: -0.0000

Data Index: 942611 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1610660 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0843. Min Act: -0.0000

Data Index: 663937 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1532410 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1439055 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0149. Min Act: -0.0000

Data Index: 538252 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.1102. Min Act: -0.0000

Data Index: 4837 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1574450 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1324204 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.4013. Min Range: -1.4013

Max Act: 1.0099. Min Act: -0.0000

Data Index: 121829 (C4 (Web Text))

Max Activating Token Index: 207