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

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

Neuron 1974 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: 6.2724. Min Range: -6.2724

Max Act: 6.2724. Min Act: -0.1488

Data Index: 1547022 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 6.2724. Min Range: -6.2724

Max Act: 6.0068. Min Act: -0.1119

Data Index: 1378544 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.9912. Min Act: -0.1240

Data Index: 1362255 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8662. Min Act: -0.1697

Data Index: 1545115 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8974. Min Act: -0.1534

Data Index: 1434802 (Python Code)

Max Activating Token Index: 400

Text #5

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8193. Min Act: -0.1698

Data Index: 1400120 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8193. Min Act: -0.1511

Data Index: 1501961 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.8037. Min Act: -0.1693

Data Index: 1599227 (Python Code)

Max Activating Token Index: 937

Text #8

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7724. Min Act: -0.1511

Data Index: 1625745 (Python Code)

Max Activating Token Index: 895

Text #9

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7568. Min Act: -0.1676

Data Index: 1411069 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7412. Min Act: -0.1696

Data Index: 1465581 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7412. Min Act: -0.1591

Data Index: 1457397 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7412. Min Act: -0.0829

Data Index: 1422207 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7099. Min Act: -0.1694

Data Index: 1494738 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7099. Min Act: -0.1161

Data Index: 1488538 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.6787. Min Act: -0.1488

Data Index: 1565366 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.6630. Min Act: -0.1277

Data Index: 1639553 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.7099. Min Act: -0.1377

Data Index: 1368219 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.6630. Min Act: -0.1688

Data Index: 1521507 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 6.2724. Min Range: -6.2724

Max Act: 5.5849. Min Act: -0.1463

Data Index: 1489583 (Python Code)

Max Activating Token Index: 914