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

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

Neuron 3745 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: 1.1687. Min Range: -1.1687

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1113451 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.9700. Min Act: 0.0000

Data Index: 408831 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.9229. Min Act: -0.0000

Data Index: 650349 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8944. Min Act: -0.0000

Data Index: 258791 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8703. Min Act: 0.0000

Data Index: 620164 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8579. Min Act: -0.0000

Data Index: 340843 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8056. Min Act: -0.0000

Data Index: 768054 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1124603 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1293679 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7500. Min Act: 0.0000

Data Index: 420615 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7583. Min Act: 0.0000

Data Index: 189144 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8045. Min Act: -0.0000

Data Index: 611084 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7524. Min Act: -0.0000

Data Index: 291755 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1490907 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6806. Min Act: -0.0000

Data Index: 113227 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1083722 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6945. Min Act: -0.0000

Data Index: 262398 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1491500 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1034636 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1346221 (C4 (Web Text))

Max Activating Token Index: 119