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

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

Neuron 3651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.6111. Min Act: -0.0000

Data Index: 1621745 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.7851. Min Act: -0.0000

Data Index: 1628626 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1379098 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.6467. Min Act: -0.0000

Data Index: 1474251 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1455553 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1435635 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1572593 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1637738 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1508875 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.5469. Min Act: -0.0000

Data Index: 1440241 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1474385 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1375584 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4752. Min Act: -0.0000

Data Index: 1576468 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1449989 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1513817 (Python Code)

Max Activating Token Index: 688

Text #15

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.3897. Min Act: -0.0000

Data Index: 1468037 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1395908 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1539485 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1482247 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 1.7851. Min Range: -1.7851

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1432882 (Python Code)

Max Activating Token Index: 594