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

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

Neuron 1786 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: 3.9649. Min Range: -3.9649

Max Act: 3.9649. Min Act: -0.1700

Data Index: 692067 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.8242. Min Act: -0.1700

Data Index: 1212888 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7772. Min Act: -0.1700

Data Index: 493959 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7772. Min Act: -0.1700

Data Index: 741545 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7616. Min Act: -0.1700

Data Index: 545723 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7303. Min Act: -0.1700

Data Index: 28297 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7303. Min Act: -0.1700

Data Index: 444859 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1205033 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7146. Min Act: -0.1700

Data Index: 132934 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7146. Min Act: -0.1700

Data Index: 360703 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7303. Min Act: -0.1700

Data Index: 87109 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 504304 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7146. Min Act: -0.1700

Data Index: 1059988 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1112986 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6834. Min Act: -0.1700

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 41198 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1199549 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6834. Min Act: -0.1700

Data Index: 1034074 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.7146. Min Act: -0.1700

Data Index: 506717 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 3.9649. Min Range: -3.9649

Max Act: 3.6990. Min Act: -0.1700

Data Index: 758011 (C4 (Web Text))

Max Activating Token Index: 5