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

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

Neuron 1767 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: 3.3873. Min Range: -3.3873

Max Act: 3.3873. Min Act: -0.1700

Data Index: 828629 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3559. Min Act: -0.1700

Data Index: 365811 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3559. Min Act: -0.1700

Data Index: 1089712 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3245. Min Act: -0.1700

Data Index: 1061760 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3245. Min Act: -0.1700

Data Index: 907190 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3245. Min Act: -0.1700

Data Index: 1264802 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3559. Min Act: -0.1700

Data Index: 561433 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3245. Min Act: -0.1700

Data Index: 1071866 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 971883 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.3245. Min Act: -0.1700

Data Index: 517868 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2617. Min Act: -0.1700

Data Index: 1275775 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 784391 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 760822 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 119047 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 299864 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2617. Min Act: -0.1700

Data Index: 241846 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 584581 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2931. Min Act: -0.1700

Data Index: 739901 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2617. Min Act: -0.1700

Data Index: 116937 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.3873. Min Range: -3.3873

Max Act: 3.2617. Min Act: -0.1700

Data Index: 471742 (C4 (Web Text))

Max Activating Token Index: 966