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

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

Neuron 1348 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: 5.0394. Min Range: -5.0394

Max Act: 5.0394. Min Act: -0.1700

Data Index: 851059 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 5.0394. Min Range: -5.0394

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1345748 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 5.0394. Min Range: -5.0394

Max Act: 5.0081. Min Act: -0.1700

Data Index: 18895 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.9769. Min Act: -0.1700

Data Index: 312053 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.9456. Min Act: -0.1700

Data Index: 194602 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.9144. Min Act: -0.1700

Data Index: 434496 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 5.0394. Min Range: -5.0394

Max Act: 5.0394. Min Act: -0.1700

Data Index: 812431 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8831. Min Act: -0.1700

Data Index: 194650 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8519. Min Act: -0.1700

Data Index: 833513 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8519. Min Act: -0.1700

Data Index: 682236 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8519. Min Act: -0.1700

Data Index: 681018 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8831. Min Act: -0.1700

Data Index: 434416 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7581. Min Act: -0.1700

Data Index: 1109732 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7894. Min Act: -0.1700

Data Index: 279720 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.8519. Min Act: -0.1700

Data Index: 298930 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7581. Min Act: -0.1700

Data Index: 241481 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7581. Min Act: -0.1700

Data Index: 1068828 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7269. Min Act: -0.1700

Data Index: 580400 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7894. Min Act: -0.1700

Data Index: 1047071 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 5.0394. Min Range: -5.0394

Max Act: 4.7894. Min Act: -0.1700

Data Index: 1076978 (C4 (Web Text))

Max Activating Token Index: 865