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

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

Neuron 690 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: 5.0121. Min Range: -5.0121

Max Act: 4.7933. Min Act: -0.1699

Data Index: 261128 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8246. Min Act: -0.1700

Data Index: 957266 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8871. Min Act: -0.1699

Data Index: 660146 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8558. Min Act: -0.1700

Data Index: 867117 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 5.0121. Min Range: -5.0121

Max Act: 5.0121. Min Act: -0.1700

Data Index: 988858 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.7933. Min Act: -0.1700

Data Index: 653460 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.9183. Min Act: -0.1699

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.9496. Min Act: -0.1700

Data Index: 1168813 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.9183. Min Act: -0.1700

Data Index: 936326 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8871. Min Act: -0.1700

Data Index: 129887 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.7621. Min Act: -0.1700

Data Index: 108475 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8246. Min Act: -0.1700

Data Index: 57385 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.7308. Min Act: -0.1700

Data Index: 1303833 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8871. Min Act: -0.1700

Data Index: 698895 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8558. Min Act: -0.1700

Data Index: 713696 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.6371. Min Act: -0.1700

Data Index: 569125 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8558. Min Act: -0.1700

Data Index: 518717 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.8558. Min Act: -0.1700

Data Index: 440904 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.7308. Min Act: -0.1699

Data Index: 409700 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 5.0121. Min Range: -5.0121

Max Act: 4.7933. Min Act: -0.1699

Data Index: 682094 (C4 (Web Text))

Max Activating Token Index: 438