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

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

Neuron 5158 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: 3.5285. Min Range: -3.5285

Max Act: 3.5285. Min Act: -0.0000

Data Index: 1375411 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.2785. Min Act: -0.0000

Data Index: 1643758 (Python Code)

Max Activating Token Index: 678

Text #2

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1450280 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1459148 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1144. Min Act: -0.0000

Data Index: 1644227 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.0882. Min Act: -0.0000

Data Index: 1485203 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1298. Min Act: -0.0000

Data Index: 1368889 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1489260 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1039. Min Act: -0.0000

Data Index: 1651395 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.0662. Min Act: -0.0000

Data Index: 1543919 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.0300. Min Act: -0.0000

Data Index: 1365205 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1567478 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1394839 (Python Code)

Max Activating Token Index: 844

Text #13

Max Range: 3.5285. Min Range: -3.5285

Max Act: 2.1025. Min Act: -0.0000

Data Index: 1404620 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1601622 (Python Code)

Max Activating Token Index: 763

Text #15

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.7711. Min Act: -0.0000

Data Index: 1522895 (Python Code)

Max Activating Token Index: 889

Text #16

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1531944 (Python Code)

Max Activating Token Index: 860

Text #17

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.9989. Min Act: -0.0000

Data Index: 1644255 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.8649. Min Act: -0.0000

Data Index: 1547443 (Python Code)

Max Activating Token Index: 743

Text #19

Max Range: 3.5285. Min Range: -3.5285

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1562261 (Python Code)

Max Activating Token Index: 161