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

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

Neuron 1852 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: 4.2150. Min Range: -4.2150

Max Act: 4.2150. Min Act: -0.1700

Data Index: 830864 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1952. Min Act: -0.1700

Data Index: 1183860 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1685. Min Act: -0.1700

Data Index: 740191 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1484. Min Act: -0.1700

Data Index: 766509 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1617. Min Act: -0.1700

Data Index: 461019 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1629. Min Act: -0.1700

Data Index: 1215605 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1484. Min Act: -0.1700

Data Index: 1094598 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1374. Min Act: -0.1700

Data Index: 836163 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1265. Min Act: -0.1700

Data Index: 1257794 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1187. Min Act: -0.1700

Data Index: 533461 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1062. Min Act: -0.1700

Data Index: 1222866 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1184. Min Act: -0.1700

Data Index: 607516 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1002. Min Act: -0.1700

Data Index: 154889 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0640. Min Act: -0.1700

Data Index: 375286 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0999. Min Act: -0.1700

Data Index: 444218 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.1054. Min Act: -0.1700

Data Index: 1139918 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0740. Min Act: -0.1700

Data Index: 346578 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0896. Min Act: -0.1700

Data Index: 11293 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0743. Min Act: -0.1700

Data Index: 382416 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 4.2150. Min Range: -4.2150

Max Act: 4.0666. Min Act: -0.1700

Data Index: 227782 (C4 (Web Text))

Max Activating Token Index: 268