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

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

Neuron 1242 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.4105. Min Act: -0.1700

Data Index: 1211350 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.3792. Min Act: -0.1700

Data Index: 1071622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2693. Min Act: -0.1700

Data Index: 702794 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2221. Min Act: -0.1700

Data Index: 636719 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1749. Min Act: -0.1700

Data Index: 1325900 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1906. Min Act: -0.1700

Data Index: 319013 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1906. Min Act: -0.1700

Data Index: 1020154 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2221. Min Act: -0.1700

Data Index: 202378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1906. Min Act: -0.1700

Data Index: 235039 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1906. Min Act: -0.1700

Data Index: 121454 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2221. Min Act: -0.1700

Data Index: 332037 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2378. Min Act: -0.1700

Data Index: 1302034 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1906. Min Act: -0.1699

Data Index: 565808 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1277. Min Act: -0.1700

Data Index: 1118837 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1592. Min Act: -0.1700

Data Index: 774301 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1592. Min Act: -0.1700

Data Index: 1171126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2064. Min Act: -0.1700

Data Index: 1302803 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.2378. Min Act: -0.1700

Data Index: 417168 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1277. Min Act: -0.1700

Data Index: 697743 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.4105. Min Range: -3.4105

Max Act: 3.1592. Min Act: -0.1700

Data Index: 1245530 (C4 (Web Text))

Max Activating Token Index: 760