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

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

Neuron 1651 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.9124. Min Act: -0.1700

Data Index: 1014008 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.8812. Min Act: -0.1700

Data Index: 1356305 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.8499. Min Act: -0.1700

Data Index: 819755 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1276227 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7873. Min Act: -0.1700

Data Index: 1159638 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7873. Min Act: -0.1700

Data Index: 1135045 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 181411 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.8186. Min Act: -0.1700

Data Index: 981880 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 961936 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 884480 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 891053 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 85754 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 225955 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1278478 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 894958 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7561. Min Act: -0.1700

Data Index: 188266 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7248. Min Act: -0.1700

Data Index: 598717 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7248. Min Act: -0.1700

Data Index: 60943 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7248. Min Act: -0.1700

Data Index: 148717 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.9124. Min Range: -3.9124

Max Act: 3.7248. Min Act: -0.1700

Data Index: 870589 (C4 (Web Text))

Max Activating Token Index: 286