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

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

Neuron 249 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2655. Min Act: -0.1700

Data Index: 1189840 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2342. Min Act: -0.1700

Data Index: 112238 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2342. Min Act: -0.1700

Data Index: 558545 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2342. Min Act: -0.1700

Data Index: 1179022 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.2030. Min Act: -0.1699

Data Index: 783137 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.1405. Min Act: -0.1700

Data Index: 118985 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.0780. Min Act: -0.1700

Data Index: 1300104 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.0467. Min Act: -0.1700

Data Index: 938149 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9842. Min Act: -0.1700

Data Index: 210791 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9530. Min Act: -0.1700

Data Index: 303686 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 5.2655. Min Range: -5.2655

Max Act: 5.0155. Min Act: -0.1700

Data Index: 403476 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9842. Min Act: -0.1700

Data Index: 624650 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9842. Min Act: -0.1700

Data Index: 1171896 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9530. Min Act: -0.1700

Data Index: 1271886 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9530. Min Act: -0.1700

Data Index: 503060 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9217. Min Act: -0.1700

Data Index: 1323167 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9217. Min Act: -0.1700

Data Index: 54159 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.8905. Min Act: -0.1700

Data Index: 836596 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9217. Min Act: -0.1700

Data Index: 670464 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 5.2655. Min Range: -5.2655

Max Act: 4.9217. Min Act: -0.1700

Data Index: 785849 (C4 (Web Text))

Max Activating Token Index: 288