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

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

Neuron 3798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0999. Min Act: -0.0000

Data Index: 1482679 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2263. Min Act: -0.0000

Data Index: 1468862 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2590. Min Act: -0.0000

Data Index: 1518872 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2356. Min Act: -0.0000

Data Index: 1360822 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.9207. Min Act: -0.0000

Data Index: 1514363 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1077. Min Act: -0.0000

Data Index: 1477806 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.8952. Min Act: -0.0000

Data Index: 1604051 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2074. Min Act: -0.0000

Data Index: 1390012 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.2923. Min Act: -0.0000

Data Index: 1644394 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1117. Min Act: -0.0000

Data Index: 1577449 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0590. Min Act: -0.0000

Data Index: 1608513 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1216. Min Act: -0.0000

Data Index: 1464455 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0803. Min Act: -0.0000

Data Index: 1598446 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.9330. Min Act: -0.0000

Data Index: 1608873 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0589. Min Act: -0.0000

Data Index: 1365778 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 3.2923. Min Range: -3.2923

Max Act: 2.8068. Min Act: -0.0000

Data Index: 1483429 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1365385 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0385. Min Act: -0.0000

Data Index: 1432633 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.1904. Min Act: -0.0000

Data Index: 1404589 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 3.2923. Min Range: -3.2923

Max Act: 3.0514. Min Act: -0.0000

Data Index: 1511532 (Python Code)

Max Activating Token Index: 604