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

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

Neuron 4396 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1580521 (Python Code)

Max Activating Token Index: 455

Text #1

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1537561 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1532425 (Python Code)

Max Activating Token Index: 259

Text #3

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.0019. Min Act: -0.0000

Data Index: 1570608 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1607583 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1507940 (Python Code)

Max Activating Token Index: 362

Text #6

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1492400 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9002. Min Act: -0.0000

Data Index: 985738 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1537714 (Python Code)

Max Activating Token Index: 768

Text #9

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1402817 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 1.2587. Min Range: -1.2587

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1558522 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1640434 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1576880 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1506551 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1367990 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1628061 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1555212 (Python Code)

Max Activating Token Index: 406

Text #17

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8971. Min Act: -0.0000

Data Index: 728866 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1405319 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 1.2587. Min Range: -1.2587

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1493901 (Python Code)

Max Activating Token Index: 517