Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1371393 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9199. Min Act: -0.0001

Data Index: 1378227 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1559093 (Python Code)

Max Activating Token Index: 864

Text #3

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1466363 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8342. Min Act: -0.0001

Data Index: 269512 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1500585 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1381713 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1495472 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1513737 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7375. Min Act: -0.0001

Data Index: 1600878 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7113. Min Act: -0.0001

Data Index: 1565634 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7137. Min Act: -0.0000

Data Index: 934288 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.6775. Min Act: 0.0001

Data Index: 1364465 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7398. Min Act: 0.0000

Data Index: 1429477 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7118. Min Act: -0.0001

Data Index: 1592907 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1569093 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7372. Min Act: -0.0000

Data Index: 447173 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1476684 (Python Code)

Max Activating Token Index: 606

Text #18

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7523. Min Act: 0.0000

Data Index: 1445677 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1560992 (Python Code)

Max Activating Token Index: 638