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

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

Neuron 524 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: 3.8875. Min Range: -3.8875

Max Act: 3.8875. Min Act: -0.1700

Data Index: 709787 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.8562. Min Act: -0.1700

Data Index: 22147 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.8249. Min Act: -0.1700

Data Index: 129466 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7936. Min Act: -0.1700

Data Index: 749562 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.8562. Min Act: -0.1700

Data Index: 815014 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.8249. Min Act: -0.1700

Data Index: 469369 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7623. Min Act: -0.1700

Data Index: 158546 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7623. Min Act: -0.1700

Data Index: 115268 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 111678 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1108775 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1133320 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7310. Min Act: -0.1700

Data Index: 1352311 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7310. Min Act: -0.1700

Data Index: 249813 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.7310. Min Act: -0.1700

Data Index: 100936 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6685. Min Act: -0.1700

Data Index: 118824 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 778623 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6685. Min Act: -0.1700

Data Index: 595126 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1257190 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6685. Min Act: -0.1700

Data Index: 1241356 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 3.8875. Min Range: -3.8875

Max Act: 3.6998. Min Act: -0.1700

Data Index: 1302399 (C4 (Web Text))

Max Activating Token Index: 187