Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 76 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.5752. Min Act: -0.1700

Data Index: 1211507 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.3252. Min Act: -0.1700

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.2627. Min Act: -0.1700

Data Index: 892401 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.1690. Min Act: -0.1700

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.1690. Min Act: -0.1700

Data Index: 991558 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.0752. Min Act: -0.1700

Data Index: 350522 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.0752. Min Act: -0.1700

Data Index: 494440 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.0752. Min Act: -0.1700

Data Index: 1174672 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.0752. Min Act: -0.1700

Data Index: 637478 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9502. Min Act: -0.1700

Data Index: 945654 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9815. Min Act: -0.1700

Data Index: 496864 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 5.5752. Min Range: -5.5752

Max Act: 5.0127. Min Act: -0.1700

Data Index: 202856 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.8877. Min Act: -0.1700

Data Index: 268547 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9190. Min Act: -0.1700

Data Index: 173441 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9502. Min Act: -0.1700

Data Index: 635523 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.8565. Min Act: -0.1700

Data Index: 1283786 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9190. Min Act: -0.1700

Data Index: 273830 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9190. Min Act: -0.1700

Data Index: 867407 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9502. Min Act: -0.1700

Data Index: 385266 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 5.5752. Min Range: -5.5752

Max Act: 4.9190. Min Act: -0.1700

Data Index: 372755 (C4 (Web Text))

Max Activating Token Index: 384