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

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

Neuron 1742 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.5697. Min Act: -0.1700

Data Index: 941823 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.4757. Min Act: -0.1700

Data Index: 410496 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3973. Min Act: -0.1700

Data Index: 549599 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.4444. Min Act: -0.1700

Data Index: 475937 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3660. Min Act: -0.1700

Data Index: 933661 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3503. Min Act: -0.1700

Data Index: 126969 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3503. Min Act: -0.1700

Data Index: 1354090 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3817. Min Act: -0.1700

Data Index: 458054 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3346. Min Act: -0.1700

Data Index: 479411 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3189. Min Act: -0.1700

Data Index: 445698 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3346. Min Act: -0.1700

Data Index: 1284869 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3346. Min Act: -0.1700

Data Index: 1153633 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3189. Min Act: -0.1700

Data Index: 1035532 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3346. Min Act: -0.1700

Data Index: 499137 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3346. Min Act: -0.1700

Data Index: 317097 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1196782 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3032. Min Act: -0.1700

Data Index: 701744 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.2875. Min Act: -0.1700

Data Index: 1316712 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3189. Min Act: -0.1700

Data Index: 105173 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 3.5697. Min Range: -3.5697

Max Act: 3.3032. Min Act: -0.1700

Data Index: 785665 (C4 (Web Text))

Max Activating Token Index: 381