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

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

Neuron 1111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8452. Min Act: -0.0002

Data Index: 1500178 (Python Code)

Max Activating Token Index: 512

Text #1

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8349. Min Act: -0.0002

Data Index: 1470632 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8199. Min Act: -0.0002

Data Index: 1568176 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7785. Min Act: -0.0002

Data Index: 1367483 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7758. Min Act: -0.0002

Data Index: 275031 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.8033. Min Act: -0.0002

Data Index: 1558976 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7851. Min Act: -0.0002

Data Index: 1586958 (Python Code)

Max Activating Token Index: 704

Text #7

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7357. Min Act: -0.0002

Data Index: 1648423 (Python Code)

Max Activating Token Index: 949

Text #8

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7198. Min Act: -0.0002

Data Index: 1559403 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6914. Min Act: -0.0002

Data Index: 1580857 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7186. Min Act: -0.0002

Data Index: 1545686 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7154. Min Act: -0.0002

Data Index: 1524929 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7113. Min Act: -0.0002

Data Index: 1570622 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7030. Min Act: -0.0002

Data Index: 1487019 (Python Code)

Max Activating Token Index: 856

Text #14

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7033. Min Act: -0.0002

Data Index: 1405508 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.7021. Min Act: -0.0002

Data Index: 1604142 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6716. Min Act: -0.0002

Data Index: 1405171 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6949. Min Act: -0.0002

Data Index: 1580333 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6912. Min Act: -0.0002

Data Index: 1409289 (Python Code)

Max Activating Token Index: 435

Text #19

Max Range: 0.8452. Min Range: -0.8452

Max Act: 0.6861. Min Act: -0.0002

Data Index: 1565479 (Python Code)

Max Activating Token Index: 440