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

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

Neuron 2187 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: 1.9522. Min Range: -1.9522

Max Act: 1.7438. Min Act: -0.0000

Data Index: 1474243 (Python Code)

Max Activating Token Index: 898

Text #1

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.9226. Min Act: -0.0000

Data Index: 1517600 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.9522. Min Act: -0.0000

Data Index: 1632715 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1583999 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.7615. Min Act: -0.0000

Data Index: 1495108 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.8450. Min Act: -0.0000

Data Index: 1436724 (Python Code)

Max Activating Token Index: 482

Text #6

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1472577 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1615184 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1537080 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1386061 (Python Code)

Max Activating Token Index: 543

Text #10

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1374640 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1529944 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4495. Min Act: -0.0000

Data Index: 1552544 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1594446 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.3311. Min Act: -0.0000

Data Index: 1368985 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1656829 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1499115 (Python Code)

Max Activating Token Index: 741

Text #17

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1433520 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1641012 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1622914 (Python Code)

Max Activating Token Index: 993