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

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

Neuron 2223 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: 2.0529. Min Range: -2.0529

Max Act: 2.0529. Min Act: -0.0000

Data Index: 1386158 (Python Code)

Max Activating Token Index: 578

Text #1

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.8729. Min Act: -0.0000

Data Index: 1637762 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1583486 (Python Code)

Max Activating Token Index: 603

Text #3

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1433301 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1414243 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1550962 (Python Code)

Max Activating Token Index: 444

Text #6

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5601. Min Act: -0.0000

Data Index: 1438041 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1458401 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5843. Min Act: -0.0000

Data Index: 1407506 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1468407 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1548042 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1384043 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1569374 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.2584. Min Act: -0.0000

Data Index: 1402525 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1593641 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4495. Min Act: -0.0000

Data Index: 1607072 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1534279 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.6000. Min Act: -0.0000

Data Index: 1401141 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4424. Min Act: -0.0000

Data Index: 1527951 (Python Code)

Max Activating Token Index: 576

Text #19

Max Range: 2.0529. Min Range: -2.0529

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1538108 (Python Code)

Max Activating Token Index: 819