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

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

Neuron 512 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: 4.5254. Min Range: -4.5254

Max Act: 4.5254. Min Act: -0.0000

Data Index: 1655933 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.6484. Min Act: -0.0000

Data Index: 1572183 (Python Code)

Max Activating Token Index: 646

Text #2

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.8368. Min Act: -0.0000

Data Index: 1574482 (Python Code)

Max Activating Token Index: 1007

Text #3

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.5799. Min Act: -0.0000

Data Index: 1604529 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.5198. Min Act: -0.0000

Data Index: 1548011 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.2911. Min Act: -0.0000

Data Index: 1640049 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.3907. Min Act: -0.0000

Data Index: 1618449 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.5422. Min Act: -0.0000

Data Index: 1431097 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.3819. Min Act: -0.0000

Data Index: 1481256 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.3839. Min Act: -0.0000

Data Index: 1542792 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.0673. Min Act: -0.0000

Data Index: 1394708 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.1934. Min Act: -0.0000

Data Index: 1596898 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.1574. Min Act: -0.0000

Data Index: 1475359 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1448026 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.0950. Min Act: -0.0000

Data Index: 1601454 (Python Code)

Max Activating Token Index: 392

Text #15

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1482682 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 4.5254. Min Range: -4.5254

Max Act: 3.0194. Min Act: -0.0000

Data Index: 1613414 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 4.5254. Min Range: -4.5254

Max Act: 2.9871. Min Act: -0.0000

Data Index: 1417964 (Python Code)

Max Activating Token Index: 875

Text #18

Max Range: 4.5254. Min Range: -4.5254

Max Act: 2.9578. Min Act: -0.0000

Data Index: 1458042 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 4.5254. Min Range: -4.5254

Max Act: 2.8139. Min Act: -0.0000

Data Index: 1395784 (Python Code)

Max Activating Token Index: 495