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

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

Neuron 1263 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.1752. Min Act: -0.1700

Data Index: 1597966 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1441793 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0806. Min Act: -0.1700

Data Index: 1656061 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1619521 (Python Code)

Max Activating Token Index: 545

Text #4

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0649. Min Act: -0.1700

Data Index: 1479925 (Python Code)

Max Activating Token Index: 803

Text #5

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0806. Min Act: -0.1700

Data Index: 694815 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0491. Min Act: -0.1700

Data Index: 1490253 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0491. Min Act: -0.1700

Data Index: 1655731 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0333. Min Act: -0.1700

Data Index: 383672 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0491. Min Act: -0.1700

Data Index: 1623042 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0491. Min Act: -0.1700

Data Index: 1625396 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0491. Min Act: -0.1700

Data Index: 1630154 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1643091 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1569894 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0333. Min Act: -0.1700

Data Index: 453875 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0017. Min Act: -0.1700

Data Index: 1378415 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0333. Min Act: -0.1700

Data Index: 1426091 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0175. Min Act: -0.1700

Data Index: 1499427 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0017. Min Act: -0.1700

Data Index: 458482 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 3.1752. Min Range: -3.1752

Max Act: 3.0017. Min Act: -0.1700

Data Index: 814050 (C4 (Web Text))

Max Activating Token Index: 506