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

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

Neuron 3313 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.7357. Min Act: -0.0001

Data Index: 1436573 (Python Code)

Max Activating Token Index: 809

Text #1

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.7256. Min Act: -0.0001

Data Index: 1594119 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4764. Min Act: -0.0001

Data Index: 1465670 (Python Code)

Max Activating Token Index: 471

Text #3

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4532. Min Act: -0.0001

Data Index: 1614345 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3756. Min Act: -0.0001

Data Index: 1440733 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.5333. Min Act: -0.0001

Data Index: 1512885 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.4298. Min Act: -0.0001

Data Index: 1371181 (Python Code)

Max Activating Token Index: 653

Text #7

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3628. Min Act: -0.0001

Data Index: 1494992 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.3605. Min Act: -0.0001

Data Index: 1548302 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1648177 (Python Code)

Max Activating Token Index: 261

Text #10

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2271. Min Act: -0.0001

Data Index: 1580771 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2581. Min Act: -0.0001

Data Index: 1438139 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2914. Min Act: -0.0001

Data Index: 1458780 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2823. Min Act: -0.0001

Data Index: 1618843 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2307. Min Act: -0.0001

Data Index: 1422345 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2151. Min Act: -0.0001

Data Index: 1596014 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1542671 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.1501. Min Act: -0.0001

Data Index: 1654194 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.1803. Min Act: -0.0001

Data Index: 1630005 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 1.7357. Min Range: -1.7357

Max Act: 1.2085. Min Act: -0.0001

Data Index: 1445576 (Python Code)

Max Activating Token Index: 245