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

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

Neuron 39 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: 3.9370. Min Range: -3.9370

Max Act: 3.9370. Min Act: -0.1700

Data Index: 1434349 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.7494. Min Act: -0.1700

Data Index: 1376997 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.7494. Min Act: -0.1700

Data Index: 1404414 (Python Code)

Max Activating Token Index: 357

Text #3

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.7494. Min Act: -0.1700

Data Index: 1533642 (Python Code)

Max Activating Token Index: 461

Text #4

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1516853 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.7181. Min Act: -0.1700

Data Index: 1498253 (Python Code)

Max Activating Token Index: 619

Text #6

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1462452 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1450922 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1380245 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1537919 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1487627 (Python Code)

Max Activating Token Index: 721

Text #11

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1493458 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1564280 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6555. Min Act: -0.1700

Data Index: 1524165 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.5615. Min Act: -0.1700

Data Index: 1434313 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.5929. Min Act: -0.1699

Data Index: 1361040 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1414078 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.5615. Min Act: -0.1700

Data Index: 1541437 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.5929. Min Act: -0.1700

Data Index: 1552898 (Python Code)

Max Activating Token Index: 857

Text #19

Max Range: 3.9370. Min Range: -3.9370

Max Act: 3.5929. Min Act: -0.1700

Data Index: 1406874 (Python Code)

Max Activating Token Index: 747