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

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

Neuron 3743 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.8248. Min Act: -0.0000

Data Index: 516694 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.7918. Min Act: -0.0000

Data Index: 300572 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.6856. Min Act: -0.0000

Data Index: 1634145 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.7937. Min Act: -0.0000

Data Index: 1615820 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1529527 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1496252 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.5231. Min Act: -0.0000

Data Index: 1395514 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.5006. Min Act: -0.0000

Data Index: 1591391 (Python Code)

Max Activating Token Index: 657

Text #8

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1600942 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1442965 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1438298 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1393009 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1570627 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1585365 (Python Code)

Max Activating Token Index: 998

Text #14

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1511844 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3997. Min Act: -0.0000

Data Index: 308214 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1530229 (Python Code)

Max Activating Token Index: 579

Text #17

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1654318 (Python Code)

Max Activating Token Index: 684

Text #18

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3735. Min Act: -0.0000

Data Index: 335073 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.8248. Min Range: -1.8248

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1439677 (Python Code)

Max Activating Token Index: 1016