Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1022 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.2269. Min Act: -0.1700

Data Index: 599217 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1746. Min Act: -0.1700

Data Index: 280057 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1316. Min Act: -0.1699

Data Index: 531096 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0967. Min Act: -0.1700

Data Index: 356638 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1204. Min Act: -0.1700

Data Index: 1087797 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1369. Min Act: -0.1700

Data Index: 82947 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1122. Min Act: -0.1700

Data Index: 1285736 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1369. Min Act: -0.1700

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0925. Min Act: -0.1572

Data Index: 235992 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1001. Min Act: -0.1700

Data Index: 692092 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0843. Min Act: -0.1700

Data Index: 1180778 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0781. Min Act: -0.1700

Data Index: 1225996 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0840. Min Act: -0.1700

Data Index: 29866 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1063. Min Act: -0.1700

Data Index: 1323250 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0788. Min Act: -0.1700

Data Index: 411378 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0779. Min Act: -0.1696

Data Index: 1322859 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.1028. Min Act: -0.1700

Data Index: 68618 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0695. Min Act: -0.1699

Data Index: 760287 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0529. Min Act: -0.1699

Data Index: 727929 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 4.2269. Min Range: -4.2269

Max Act: 4.0617. Min Act: -0.1700

Data Index: 1247857 (C4 (Web Text))

Max Activating Token Index: 418