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

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

Neuron 584 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: 3.5733. Min Range: -3.5733

Max Act: 3.5420. Min Act: -0.1700

Data Index: 110886 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5733. Min Act: -0.1700

Data Index: 67808 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5733. Min Act: -0.1700

Data Index: 507660 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5420. Min Act: -0.1700

Data Index: 1069244 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5420. Min Act: -0.1700

Data Index: 942485 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 119538 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 81636 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 1346567 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 1270342 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 580886 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 849385 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 1099221 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 1220046 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 246609 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 1245820 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 93676 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.5107. Min Act: -0.1700

Data Index: 696111 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4480. Min Act: -0.1700

Data Index: 292314 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4480. Min Act: -0.1700

Data Index: 10788 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.5733. Min Range: -3.5733

Max Act: 3.4793. Min Act: -0.1700

Data Index: 297204 (C4 (Web Text))

Max Activating Token Index: 199