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

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

Neuron 1311 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: 8.0769. Min Range: -8.0769

Max Act: 8.0769. Min Act: -0.1700

Data Index: 53389 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 8.0769. Min Range: -8.0769

Max Act: 8.0144. Min Act: -0.1700

Data Index: 317189 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8894. Min Act: -0.1700

Data Index: 158776 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8894. Min Act: -0.1700

Data Index: 845796 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8581. Min Act: -0.1679

Data Index: 873746 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8269. Min Act: -0.1700

Data Index: 1347583 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8269. Min Act: -0.1700

Data Index: 487624 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7644. Min Act: -0.1700

Data Index: 687971 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.8269. Min Act: -0.1700

Data Index: 1299645 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7644. Min Act: -0.1700

Data Index: 1148800 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7644. Min Act: -0.1700

Data Index: 1182723 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7019. Min Act: -0.1700

Data Index: 688301 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7331. Min Act: -0.1700

Data Index: 1213353 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7019. Min Act: -0.1700

Data Index: 488561 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7331. Min Act: -0.1700

Data Index: 655741 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7019. Min Act: -0.1700

Data Index: 386067 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7644. Min Act: -0.1700

Data Index: 459138 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.6394. Min Act: -0.1699

Data Index: 1151083 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.7019. Min Act: -0.1700

Data Index: 691044 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 8.0769. Min Range: -8.0769

Max Act: 7.6706. Min Act: -0.1698

Data Index: 531259 (C4 (Web Text))

Max Activating Token Index: 970