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

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

Neuron 63 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1432221 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.1855. Min Act: -0.0001

Data Index: 1546341 (Python Code)

Max Activating Token Index: 987

Text #2

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1498867 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1590996 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1652693 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1537364 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1604351 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1524764 (Python Code)

Max Activating Token Index: 843

Text #8

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1427575 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1558216 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1427792 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1648410 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1382356 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1480584 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1505625 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.2114. Min Range: -1.2114

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1579155 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1417832 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9783. Min Act: -0.0000

Data Index: 1598966 (Python Code)

Max Activating Token Index: 447

Text #18

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.8383. Min Act: -0.0001

Data Index: 1481476 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 1.2114. Min Range: -1.2114

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1569923 (Python Code)

Max Activating Token Index: 975