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

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

Neuron 502 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: 7.7912. Min Range: -7.7912

Max Act: 7.7912. Min Act: -0.1700

Data Index: 536074 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.3849. Min Act: -0.1700

Data Index: 783725 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.2912. Min Act: -0.1700

Data Index: 463547 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.2912. Min Act: -0.1700

Data Index: 845682 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.1349. Min Act: -0.1700

Data Index: 434533 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.1037. Min Act: -0.1700

Data Index: 943926 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.0412. Min Act: -0.1700

Data Index: 621449 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.1037. Min Act: -0.1700

Data Index: 545230 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.0099. Min Act: -0.1700

Data Index: 985880 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.0099. Min Act: -0.1700

Data Index: 569077 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.0412. Min Act: -0.1700

Data Index: 906770 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 7.7912. Min Range: -7.7912

Max Act: 7.0099. Min Act: -0.1700

Data Index: 291446 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9474. Min Act: -0.1699

Data Index: 1149001 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9787. Min Act: -0.1700

Data Index: 1193296 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9474. Min Act: -0.1700

Data Index: 1268527 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9474. Min Act: -0.1700

Data Index: 414678 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9162. Min Act: -0.1700

Data Index: 1125804 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9162. Min Act: -0.1700

Data Index: 476882 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.9474. Min Act: -0.1700

Data Index: 640387 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 7.7912. Min Range: -7.7912

Max Act: 6.8849. Min Act: -0.1700

Data Index: 117839 (C4 (Web Text))

Max Activating Token Index: 129