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

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

Neuron 380 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: 3.6722. Min Range: -3.6722

Max Act: 3.6722. Min Act: -0.1700

Data Index: 747840 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6722. Min Act: -0.1700

Data Index: 1038432 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6409. Min Act: -0.1700

Data Index: 356951 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6409. Min Act: -0.1700

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 438297 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 1097276 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6409. Min Act: -0.1700

Data Index: 1322233 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 551302 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 407771 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 172131 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 668028 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 670261 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 694632 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 1144968 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1156788 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 1239254 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 1308088 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 872825 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.5782. Min Act: -0.1700

Data Index: 952905 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 3.6722. Min Range: -3.6722

Max Act: 3.6096. Min Act: -0.1700

Data Index: 201244 (C4 (Web Text))

Max Activating Token Index: 748