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

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

Neuron 365 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: 3.9011. Min Range: -3.9011

Max Act: 3.8698. Min Act: -0.1700

Data Index: 668846 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.8698. Min Act: -0.1700

Data Index: 682994 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.9011. Min Act: -0.1700

Data Index: 408169 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.8385. Min Act: -0.1700

Data Index: 520849 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.8385. Min Act: -0.1700

Data Index: 1115750 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.8073. Min Act: -0.1700

Data Index: 323414 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7760. Min Act: -0.1700

Data Index: 1240362 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7760. Min Act: -0.1700

Data Index: 361026 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7760. Min Act: -0.1700

Data Index: 151255 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7447. Min Act: -0.1700

Data Index: 811517 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7447. Min Act: -0.1700

Data Index: 270074 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7760. Min Act: -0.1700

Data Index: 1273877 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7134. Min Act: -0.1700

Data Index: 113988 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.6821. Min Act: -0.1700

Data Index: 660599 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7134. Min Act: -0.1700

Data Index: 986825 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.6821. Min Act: -0.1700

Data Index: 805300 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.7134. Min Act: -0.1700

Data Index: 553966 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.6821. Min Act: -0.1700

Data Index: 671770 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.6821. Min Act: -0.1700

Data Index: 15760 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.9011. Min Range: -3.9011

Max Act: 3.6508. Min Act: -0.1700

Data Index: 708975 (C4 (Web Text))

Max Activating Token Index: 343