Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2039 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.7899. Min Act: -0.1700

Data Index: 1535322 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.8837. Min Act: -0.1700

Data Index: 1542552 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.7274. Min Act: -0.1700

Data Index: 1417910 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.7274. Min Act: -0.1700

Data Index: 1554781 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6649. Min Act: -0.1700

Data Index: 1371302 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6962. Min Act: -0.1700

Data Index: 1608268 (Python Code)

Max Activating Token Index: 452

Text #6

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6649. Min Act: -0.1700

Data Index: 1642608 (Python Code)

Max Activating Token Index: 613

Text #7

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6649. Min Act: -0.1700

Data Index: 1609251 (Python Code)

Max Activating Token Index: 395

Text #8

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1548209 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6024. Min Act: -0.1620

Data Index: 1388159 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1429272 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.6024. Min Act: -0.1700

Data Index: 1582284 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.5399. Min Act: -0.1700

Data Index: 1481719 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.4462. Min Act: -0.1700

Data Index: 1508313 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.4774. Min Act: -0.1700

Data Index: 1520505 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.4774. Min Act: -0.1700

Data Index: 1380824 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.4774. Min Act: -0.1700

Data Index: 1577391 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.4462. Min Act: -0.1700

Data Index: 1474129 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.5399. Min Act: -0.1700

Data Index: 1500357 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 5.8837. Min Range: -5.8837

Max Act: 5.5087. Min Act: -0.1700

Data Index: 1476327 (Python Code)

Max Activating Token Index: 837