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

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

Neuron 1725 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.7344. Min Act: -0.1700

Data Index: 864265 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.7657. Min Act: -0.1700

Data Index: 354330 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.7188. Min Act: -0.1700

Data Index: 1602020 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.6405. Min Act: -0.1700

Data Index: 386083 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.6562. Min Act: -0.1700

Data Index: 273946 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1285911 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.6092. Min Act: -0.1700

Data Index: 335513 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5466. Min Act: -0.1700

Data Index: 93754 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.6092. Min Act: -0.1700

Data Index: 1439351 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5466. Min Act: -0.1700

Data Index: 29688 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5309. Min Act: -0.1700

Data Index: 168002 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5152. Min Act: -0.1700

Data Index: 539774 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1260159 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5466. Min Act: -0.1700

Data Index: 865945 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5622. Min Act: -0.1700

Data Index: 568518 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1194350 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.4996. Min Act: -0.1700

Data Index: 1019506 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.4839. Min Act: -0.1700

Data Index: 897865 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.4996. Min Act: -0.1700

Data Index: 1043012 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 3.7657. Min Range: -3.7657

Max Act: 3.5152. Min Act: -0.1700

Data Index: 661743 (C4 (Web Text))

Max Activating Token Index: 467