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

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

Neuron 639 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: 3.9194. Min Range: -3.9194

Max Act: 3.9194. Min Act: -0.1688

Data Index: 1060115 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.9194. Min Act: -0.1699

Data Index: 1012380 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8725. Min Act: -0.1700

Data Index: 376762 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8412. Min Act: -0.1700

Data Index: 84320 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8256. Min Act: -0.1700

Data Index: 484009 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8412. Min Act: -0.1700

Data Index: 483527 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8100. Min Act: -0.1700

Data Index: 1266425 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8256. Min Act: -0.1699

Data Index: 1261477 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7943. Min Act: -0.1699

Data Index: 989497 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.8412. Min Act: -0.1636

Data Index: 952458 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7787. Min Act: -0.1700

Data Index: 696613 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7474. Min Act: -0.1700

Data Index: 141510 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1355800 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7474. Min Act: -0.1695

Data Index: 528193 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7161. Min Act: -0.1700

Data Index: 962201 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7161. Min Act: -0.1700

Data Index: 807377 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7474. Min Act: -0.1700

Data Index: 1327926 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1103501 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7317. Min Act: -0.1700

Data Index: 3859 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 3.9194. Min Range: -3.9194

Max Act: 3.7005. Min Act: -0.1700

Data Index: 155982 (C4 (Web Text))

Max Activating Token Index: 813