Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 33 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.6051. Min Act: -0.1700

Data Index: 1220006 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.2926. Min Act: -0.1700

Data Index: 1117913 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.1989. Min Act: -0.1700

Data Index: 1196292 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.1051. Min Act: -0.1700

Data Index: 190691 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.0426. Min Act: -0.1700

Data Index: 595922 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.0426. Min Act: -0.1700

Data Index: 629030 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9801. Min Act: -0.1700

Data Index: 1228649 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 5.6051. Min Range: -5.6051

Max Act: 5.0114. Min Act: -0.1700

Data Index: 37788 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9801. Min Act: -0.1700

Data Index: 737964 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9801. Min Act: -0.1700

Data Index: 26909 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9489. Min Act: -0.1700

Data Index: 294395 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9489. Min Act: -0.1700

Data Index: 539826 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9176. Min Act: -0.1700

Data Index: 762012 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.9176. Min Act: -0.1700

Data Index: 1146445 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8864. Min Act: -0.1700

Data Index: 174191 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8551. Min Act: -0.1700

Data Index: 199822 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8239. Min Act: -0.1700

Data Index: 394884 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8239. Min Act: -0.1699

Data Index: 330084 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8551. Min Act: -0.1700

Data Index: 538718 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 5.6051. Min Range: -5.6051

Max Act: 4.8551. Min Act: -0.1700

Data Index: 218957 (C4 (Web Text))

Max Activating Token Index: 213