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

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

Neuron 1261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.6305. Min Act: -0.1530

Data Index: 159547 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.6618. Min Act: -0.1280

Data Index: 733954 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5993. Min Act: -0.1675

Data Index: 459224 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5368. Min Act: -0.1538

Data Index: 368203 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5680. Min Act: -0.1652

Data Index: 900289 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5993. Min Act: -0.1680

Data Index: 1268877 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5680. Min Act: -0.1648

Data Index: 982382 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5368. Min Act: -0.1592

Data Index: 100256 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5368. Min Act: -0.1658

Data Index: 1314119 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1614

Data Index: 560042 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5368. Min Act: -0.1543

Data Index: 821407 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.4743. Min Act: -0.1655

Data Index: 95411 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1599

Data Index: 1236924 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1490

Data Index: 731399 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.4743. Min Act: -0.1610

Data Index: 1263368 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1635

Data Index: 866157 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.4743. Min Act: -0.1452

Data Index: 171185 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1628

Data Index: 460946 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.5055. Min Act: -0.1606

Data Index: 334269 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 5.6618. Min Range: -5.6618

Max Act: 5.4430. Min Act: -0.1484

Data Index: 58388 (C4 (Web Text))

Max Activating Token Index: 805