Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1680. Min Range: -5.1680
Max Act: 5.1680. Min Act: -0.1700
Data Index: 696978 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1680. Min Range: -5.1680
Max Act: 5.0117. Min Act: -0.1700
Data Index: 5703792 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 664616 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 3811785 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1680. Min Range: -5.1680
Max Act: 5.0117. Min Act: -0.1700
Data Index: 6953649 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1680. Min Range: -5.1680
Max Act: 5.0117. Min Act: -0.1700
Data Index: 6166850 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 7531196 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 658779 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1680. Min Range: -5.1680
Max Act: 5.0117. Min Act: -0.1700
Data Index: 5225229 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 1972939 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 1294253 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 7786356 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 7740357 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 1175222 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 6219084 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 5274049 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 7349738 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9805. Min Act: -0.1700
Data Index: 1562453 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 2477836 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1680. Min Range: -5.1680
Max Act: 4.9492. Min Act: -0.1700
Data Index: 2613537 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19