Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8830. Min Act: -0.0000

Data Index: 1571483 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1590303 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7205. Min Act: -0.0000

Data Index: 1423922 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1517128 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1640960 (Python Code)

Max Activating Token Index: 145

Text #5

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1462623 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7205. Min Act: -0.0000

Data Index: 1487073 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1557625 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1456736 (Python Code)

Max Activating Token Index: 964

Text #9

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1406782 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1510133 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1628098 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6490. Min Act: -0.0000

Data Index: 1574059 (Python Code)

Max Activating Token Index: 647

Text #13

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1427582 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4354. Min Act: -0.0000

Data Index: 1518733 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1507279 (Python Code)

Max Activating Token Index: 295

Text #16

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1501827 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1553448 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1504414 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 1.8830. Min Range: -1.8830

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1587627 (Python Code)

Max Activating Token Index: 47