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

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

Neuron 1837 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: 5.0412. Min Range: -5.0412

Max Act: 5.0412. Min Act: -0.1700

Data Index: 171365 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.8224. Min Act: -0.1700

Data Index: 993547 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.8224. Min Act: -0.1700

Data Index: 1096975 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.8224. Min Act: -0.1700

Data Index: 243556 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7599. Min Act: -0.1700

Data Index: 997179 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7599. Min Act: -0.1700

Data Index: 95359 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7912. Min Act: -0.1700

Data Index: 939793 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7599. Min Act: -0.1700

Data Index: 1190077 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7599. Min Act: -0.1700

Data Index: 665469 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7599. Min Act: -0.1700

Data Index: 424208 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6974. Min Act: -0.1700

Data Index: 1122083 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7287. Min Act: -0.1700

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6974. Min Act: -0.1700

Data Index: 842693 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.7287. Min Act: -0.1700

Data Index: 131527 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6037. Min Act: -0.1700

Data Index: 1228877 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6662. Min Act: -0.1700

Data Index: 1044517 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6349. Min Act: -0.1700

Data Index: 804144 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6349. Min Act: -0.1700

Data Index: 120 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6662. Min Act: -0.1700

Data Index: 1221746 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 5.0412. Min Range: -5.0412

Max Act: 4.6037. Min Act: -0.1700

Data Index: 43722 (C4 (Web Text))

Max Activating Token Index: 845