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

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

Neuron 266 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: 5.0715. Min Range: -5.0715

Max Act: 5.0715. Min Act: -0.1699

Data Index: 362908 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.9777. Min Act: -0.1699

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.9152. Min Act: -0.1699

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.8840. Min Act: -0.1700

Data Index: 989087 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.8840. Min Act: -0.1700

Data Index: 1290420 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.8215. Min Act: -0.1699

Data Index: 1101321 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7590. Min Act: -0.1700

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7902. Min Act: -0.1700

Data Index: 761140 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.8371. Min Act: -0.1700

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.8059. Min Act: -0.1700

Data Index: 552395 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7121. Min Act: -0.1699

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7746. Min Act: -0.1700

Data Index: 375558 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7902. Min Act: -0.1700

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7902. Min Act: -0.1700

Data Index: 661718 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7746. Min Act: -0.1700

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.6965. Min Act: -0.1699

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7121. Min Act: -0.1699

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7121. Min Act: -0.1700

Data Index: 799042 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.7590. Min Act: -0.1700

Data Index: 755830 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 5.0715. Min Range: -5.0715

Max Act: 4.6809. Min Act: -0.1699

Data Index: 678959 (C4 (Web Text))

Max Activating Token Index: 944