Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1314 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.1231. Min Range: -8.1231

Max Act: 8.1231. Min Act: -0.1668

Data Index: 1555537 (Python Code)

Max Activating Token Index: 500

Text #1

Max Range: 8.1231. Min Range: -8.1231

Max Act: 8.0918. Min Act: -0.1598

Data Index: 1427069 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.9981. Min Act: -0.1700

Data Index: 1526523 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.9043. Min Act: -0.1698

Data Index: 1492063 (Python Code)

Max Activating Token Index: 390

Text #4

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.9356. Min Act: -0.1700

Data Index: 1446101 (Python Code)

Max Activating Token Index: 962

Text #5

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.8418. Min Act: -0.1682

Data Index: 1549488 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.7793. Min Act: -0.1598

Data Index: 1474268 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.7793. Min Act: -0.0805

Data Index: 1431537 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.7481. Min Act: -0.1524

Data Index: 1512138 (Python Code)

Max Activating Token Index: 282

Text #9

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.7168. Min Act: -0.1676

Data Index: 1585991 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.6856. Min Act: -0.1078

Data Index: 1635465 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.5918. Min Act: -0.1680

Data Index: 1364766 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.5606. Min Act: -0.1583

Data Index: 1523294 (Python Code)

Max Activating Token Index: 593

Text #13

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.4981. Min Act: -0.1698

Data Index: 1566665 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.4668. Min Act: 0.0361

Data Index: 1366586 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.4668. Min Act: 0.1593

Data Index: 1563650 (Python Code)

Max Activating Token Index: 353

Text #16

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.4356. Min Act: -0.1699

Data Index: 1395977 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.2481. Min Act: -0.1632

Data Index: 1392605 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.2481. Min Act: -0.1700

Data Index: 1648581 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 8.1231. Min Range: -8.1231

Max Act: 7.2168. Min Act: -0.1698

Data Index: 1583554 (Python Code)

Max Activating Token Index: 280