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

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

Neuron 698 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: 3.3184. Min Range: -3.3184

Max Act: 3.1960. Min Act: -0.0000

Data Index: 1533359 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 3.3184. Min Range: -3.3184

Max Act: 3.3184. Min Act: -0.0000

Data Index: 1627059 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 3.3184. Min Range: -3.3184

Max Act: 3.2233. Min Act: -0.0000

Data Index: 1373261 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.7205. Min Act: -0.0000

Data Index: 1366174 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.8263. Min Act: -0.0000

Data Index: 1452563 (Python Code)

Max Activating Token Index: 1007

Text #5

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.9495. Min Act: -0.0000

Data Index: 1411304 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1468805 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.6702. Min Act: -0.0000

Data Index: 1533764 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.7269. Min Act: -0.0000

Data Index: 1597953 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.4972. Min Act: -0.0000

Data Index: 1431028 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.6727. Min Act: -0.0000

Data Index: 1468589 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.5013. Min Act: -0.0000

Data Index: 1641792 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.2972. Min Act: -0.0000

Data Index: 1385971 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.5783. Min Act: 0.0000

Data Index: 1446282 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.2168. Min Act: -0.0000

Data Index: 1432043 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1378334 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.4396. Min Act: -0.0000

Data Index: 1567102 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.1934. Min Act: -0.0000

Data Index: 1412060 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.1491. Min Act: -0.0000

Data Index: 1404445 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 3.3184. Min Range: -3.3184

Max Act: 2.1408. Min Act: -0.0000

Data Index: 1534122 (Python Code)

Max Activating Token Index: 411