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

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

Neuron 3098 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0691. Min Act: -0.0001

Data Index: 1362369 (Python Code)

Max Activating Token Index: 679

Text #1

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.1676. Min Act: -0.0001

Data Index: 1595125 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0715. Min Act: -0.0001

Data Index: 1463564 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0481. Min Act: -0.0001

Data Index: 1494594 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9894. Min Act: -0.0001

Data Index: 1388772 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0323. Min Act: -0.0001

Data Index: 1581119 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9677. Min Act: -0.0001

Data Index: 1581346 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1494510 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 1.1676. Min Range: -1.1676

Max Act: 1.0213. Min Act: -0.0001

Data Index: 1567819 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9766. Min Act: -0.0001

Data Index: 1489498 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9405. Min Act: -0.0001

Data Index: 1365000 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9661. Min Act: -0.0001

Data Index: 1607869 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9592. Min Act: -0.0001

Data Index: 1645330 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1523434 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1573785 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1577718 (Python Code)

Max Activating Token Index: 423

Text #16

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9700. Min Act: -0.0001

Data Index: 1590930 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1493672 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.8642. Min Act: -0.0001

Data Index: 1372486 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 1.1676. Min Range: -1.1676

Max Act: 0.9538. Min Act: -0.0001

Data Index: 1431471 (Python Code)

Max Activating Token Index: 926