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

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

Neuron 2044 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1622427 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1568578 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1643577 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1526757 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1634907 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1484607 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1543908 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1456979 (Python Code)

Max Activating Token Index: 646

Text #8

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1603334 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1374012 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1428735 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1537130 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1461228 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1611308 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1426740 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1489719 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1507611 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1377903 (Python Code)

Max Activating Token Index: 888

Text #18

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1478242 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1568411 (Python Code)

Max Activating Token Index: 400