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

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

Neuron 1433 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: 3.3113. Min Range: -3.3113

Max Act: 3.3113. Min Act: -0.1700

Data Index: 967835 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 3.3113. Min Range: -3.3113

Max Act: 3.0910. Min Act: -0.1700

Data Index: 1194355 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 3.3113. Min Range: -3.3113

Max Act: 3.1225. Min Act: -0.1700

Data Index: 633036 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 3.3113. Min Range: -3.3113

Max Act: 3.0595. Min Act: -0.1700

Data Index: 234787 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 3.3113. Min Range: -3.3113

Max Act: 3.0279. Min Act: -0.1700

Data Index: 986929 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.3113. Min Range: -3.3113

Max Act: 3.0437. Min Act: -0.1700

Data Index: 1118141 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9805. Min Act: -0.1700

Data Index: 369773 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9963. Min Act: -0.1700

Data Index: 541966 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9330. Min Act: -0.1700

Data Index: 777544 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9646. Min Act: -0.1700

Data Index: 400222 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9646. Min Act: -0.1700

Data Index: 954841 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9171. Min Act: -0.1700

Data Index: 178494 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9330. Min Act: -0.1700

Data Index: 871739 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.9013. Min Act: -0.1700

Data Index: 1009743 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8695. Min Act: -0.1700

Data Index: 235800 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8854. Min Act: -0.1700

Data Index: 673442 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8218. Min Act: -0.1700

Data Index: 1265054 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8854. Min Act: -0.1700

Data Index: 609518 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8695. Min Act: -0.1700

Data Index: 251931 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 3.3113. Min Range: -3.3113

Max Act: 2.8695. Min Act: -0.1700

Data Index: 658443 (C4 (Web Text))

Max Activating Token Index: 271