Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.6743. Min Act: -0.0000

Data Index: 1591226 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.7203. Min Act: -0.0000

Data Index: 1610790 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.9286. Min Act: -0.0000

Data Index: 1394011 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.2930. Min Act: -0.0000

Data Index: 1433820 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.2628. Min Act: -0.0000

Data Index: 1568621 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.3515. Min Act: -0.0000

Data Index: 1489449 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.0910. Min Act: -0.0000

Data Index: 1456480 (Python Code)

Max Activating Token Index: 214

Text #7

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.8693. Min Act: -0.0000

Data Index: 1463190 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.0538. Min Act: -0.0000

Data Index: 1556133 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.9246. Min Act: -0.0000

Data Index: 1498604 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.8699. Min Act: -0.0000

Data Index: 1613434 (Python Code)

Max Activating Token Index: 891

Text #11

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.8716. Min Act: -0.0000

Data Index: 1568736 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 6.7203. Min Range: -6.7203

Max Act: 6.0738. Min Act: -0.0000

Data Index: 1417099 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.8476. Min Act: -0.0000

Data Index: 1485689 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.7440. Min Act: -0.0000

Data Index: 1654350 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.6944. Min Act: -0.0000

Data Index: 1539421 (Python Code)

Max Activating Token Index: 588

Text #16

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.6188. Min Act: -0.0000

Data Index: 1562247 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.5494. Min Act: -0.0000

Data Index: 1461718 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.5062. Min Act: -0.0000

Data Index: 1373366 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 6.7203. Min Range: -6.7203

Max Act: 5.2625. Min Act: -0.0000

Data Index: 1518919 (Python Code)

Max Activating Token Index: 335