Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2029 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1563. Min Range: -6.1563
Max Act: 6.1563. Min Act: -0.1700
Data Index: 7525559 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1563. Min Range: -6.1563
Max Act: 6.1563. Min Act: -0.1700
Data Index: 6559466 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1563. Min Range: -6.1563
Max Act: 6.0938. Min Act: -0.1700
Data Index: 2669653 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1563. Min Range: -6.1563
Max Act: 6.0313. Min Act: -0.1700
Data Index: 5565468 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1563. Min Range: -6.1563
Max Act: 6.0001. Min Act: -0.1700
Data Index: 8668977 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2619831 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.9063. Min Act: -0.1700
Data Index: 5801648 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.9063. Min Act: -0.1700
Data Index: 718949 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8751. Min Act: -0.1700
Data Index: 6619542 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 6199283 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 4425165 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 7667489 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 5806188 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 5395462 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8438. Min Act: -0.1700
Data Index: 1375893 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8126. Min Act: -0.1700
Data Index: 8261659 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8126. Min Act: -0.1700
Data Index: 3285404 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8126. Min Act: -0.1700
Data Index: 3067166 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.8126. Min Act: -0.1700
Data Index: 1563376 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1563. Min Range: -6.1563
Max Act: 5.7813. Min Act: -0.1700
Data Index: 6073866 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19