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

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

Neuron 3647 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1578869 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1520426 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1490336 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1501288 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1571576 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1419981 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1651696 (Python Code)

Max Activating Token Index: 888

Text #7

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1400136 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1625561 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1393089 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1398492 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1416822 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1651565 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1598350 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1481313 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1530977 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1606591 (Python Code)

Max Activating Token Index: 800

Text #17

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1409799 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1446926 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4468. Min Act: 0.0000

Data Index: 1627183 (Python Code)

Max Activating Token Index: 834