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

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

Neuron 1403 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4013. Min Range: -8.4013

Max Act: 8.4013. Min Act: -0.1700

Data Index: 1221914 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.4638. Min Act: -0.1700

Data Index: 1029670 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.4638. Min Act: -0.1700

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.2763. Min Act: -0.1700

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.2451. Min Act: -0.1699

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.1826. Min Act: -0.1698

Data Index: 1044665 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.0888. Min Act: -0.1699

Data Index: 1059305 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.1201. Min Act: -0.1697

Data Index: 116935 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.1513. Min Act: -0.1700

Data Index: 737504 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.1201. Min Act: -0.1699

Data Index: 1038037 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.0576. Min Act: -0.1695

Data Index: 863604 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.9951. Min Act: -0.1700

Data Index: 679818 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.0263. Min Act: -0.1700

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 8.4013. Min Range: -8.4013

Max Act: 7.0263. Min Act: -0.1700

Data Index: 1016804 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.9951. Min Act: -0.1700

Data Index: 366448 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.9638. Min Act: -0.1700

Data Index: 21733 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.9638. Min Act: -0.1700

Data Index: 1112343 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.9326. Min Act: -0.1700

Data Index: 841818 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.8701. Min Act: -0.1699

Data Index: 851476 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 8.4013. Min Range: -8.4013

Max Act: 6.8388. Min Act: -0.1682

Data Index: 6816 (C4 (Web Text))

Max Activating Token Index: 869