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

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

Neuron 4666 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1379272 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1594364 (Python Code)

Max Activating Token Index: 319

Text #2

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1639798 (Python Code)

Max Activating Token Index: 720

Text #3

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1416546 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1606067 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1634488 (Python Code)

Max Activating Token Index: 453

Text #6

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1655033 (Python Code)

Max Activating Token Index: 712

Text #7

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1654914 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1371965 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1528704 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1497537 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1382267 (Python Code)

Max Activating Token Index: 79

Text #12

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1550030 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1493465 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1363841 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1620886 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1491730 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1496164 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1493167 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 0.6534. Min Range: -0.6534

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1482386 (Python Code)

Max Activating Token Index: 545