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

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

Neuron 1420 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: 5.1018. Min Range: -5.1018

Max Act: 5.1018. Min Act: -0.1700

Data Index: 1040182 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 5.1018. Min Range: -5.1018

Max Act: 5.0393. Min Act: -0.1700

Data Index: 84515 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.8206. Min Act: -0.1700

Data Index: 618694 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.9143. Min Act: -0.1700

Data Index: 1098880 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.9143. Min Act: -0.1700

Data Index: 386294 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.8518. Min Act: -0.1700

Data Index: 28903 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.8831. Min Act: -0.1700

Data Index: 284288 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.9768. Min Act: -0.1700

Data Index: 870474 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.7268. Min Act: -0.1700

Data Index: 687998 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.8518. Min Act: -0.1700

Data Index: 972796 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6956. Min Act: -0.1700

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.7112. Min Act: -0.1700

Data Index: 309272 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6643. Min Act: -0.1700

Data Index: 1065492 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6956. Min Act: -0.1700

Data Index: 25781 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6174. Min Act: -0.1700

Data Index: 86010 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6018. Min Act: -0.1700

Data Index: 306966 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.5549. Min Act: -0.1700

Data Index: 965703 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6018. Min Act: -0.1700

Data Index: 768770 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.5393. Min Act: -0.1700

Data Index: 696055 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 5.1018. Min Range: -5.1018

Max Act: 4.6799. Min Act: -0.1700

Data Index: 310441 (C4 (Web Text))

Max Activating Token Index: 618