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

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

Neuron 1513 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.5367. Min Act: -0.0001

Data Index: 1621453 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.3896. Min Act: -0.0001

Data Index: 1612002 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.3881. Min Act: -0.0001

Data Index: 1525822 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.4453. Min Act: -0.0001

Data Index: 1651524 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.4023. Min Act: -0.0001

Data Index: 1431119 (Python Code)

Max Activating Token Index: 506

Text #5

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2375. Min Act: -0.0001

Data Index: 1550497 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1563306 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2968. Min Act: -0.0001

Data Index: 1432023 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2837. Min Act: -0.0001

Data Index: 1466523 (Python Code)

Max Activating Token Index: 1006

Text #9

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2771. Min Act: -0.0001

Data Index: 1475783 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2721. Min Act: -0.0001

Data Index: 1592390 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1618751 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.3337. Min Act: -0.0001

Data Index: 1567819 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2569. Min Act: -0.0001

Data Index: 1456866 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1600098 (Python Code)

Max Activating Token Index: 609

Text #15

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2415. Min Act: -0.0001

Data Index: 1419331 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2477. Min Act: -0.0001

Data Index: 1589689 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2383. Min Act: -0.0001

Data Index: 1585597 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.1602. Min Act: -0.0001

Data Index: 1431992 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 1.5367. Min Range: -1.5367

Max Act: 1.2252. Min Act: -0.0001

Data Index: 1562481 (Python Code)

Max Activating Token Index: 792