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

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

Neuron 4825 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.6139. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5565. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5362. Min Act: -0.0000

Data Index: 10733 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4073. Min Act: -0.0000

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4561. Min Act: -0.0000

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3787. Min Act: -0.0000

Data Index: 436657 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3657. Min Act: -0.0000

Data Index: 105526 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3589. Min Act: -0.0000

Data Index: 710799 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3715. Min Act: -0.0000

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3491. Min Act: -0.0000

Data Index: 570692 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1395521 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3157. Min Act: -0.0000

Data Index: 500575 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1245854 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1017075 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3076. Min Act: -0.0000

Data Index: 626221 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.2987. Min Act: -0.0000

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.2724. Min Act: -0.0000

Data Index: 1188562 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1424701 (Python Code)

Max Activating Token Index: 889

Text #19

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.2807. Min Act: -0.0000

Data Index: 801659 (C4 (Web Text))

Max Activating Token Index: 303