Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1502490 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7343. Min Act: -0.1700

Data Index: 1460299 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1538474 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6717. Min Act: -0.1700

Data Index: 1538222 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1612896 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1485489 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7030. Min Act: -0.1700

Data Index: 1512373 (Python Code)

Max Activating Token Index: 345

Text #7

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1600439 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6874. Min Act: -0.1700

Data Index: 1578708 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.7030. Min Act: -0.1700

Data Index: 1633378 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1501536 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6248. Min Act: -0.1700

Data Index: 1505322 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1423448 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6561. Min Act: -0.1700

Data Index: 1617920 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6717. Min Act: -0.1700

Data Index: 1369501 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1418803 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6561. Min Act: -0.1700

Data Index: 1448612 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1278977 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1372410 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 3.7343. Min Range: -3.7343

Max Act: 3.6248. Min Act: -0.1700

Data Index: 1428900 (Python Code)

Max Activating Token Index: 668