Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2183 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.7562. Min Act: -0.1700
Data Index: 4875738 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.4437. Min Act: -0.1700
Data Index: 331695 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.3187. Min Act: -0.1700
Data Index: 2591596 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.3187. Min Act: -0.1700
Data Index: 4452045 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.3812. Min Act: -0.1700
Data Index: 3682927 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.2562. Min Act: -0.1700
Data Index: 7081383 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.3187. Min Act: -0.1700
Data Index: 4967714 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.2562. Min Act: -0.1700
Data Index: 7081379 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1937. Min Act: -0.1700
Data Index: 4872583 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1937. Min Act: -0.1700
Data Index: 278532 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1937. Min Act: -0.1700
Data Index: 1540626 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1312. Min Act: -0.1700
Data Index: 1246161 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1937. Min Act: -0.1700
Data Index: 831739 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0687. Min Act: -0.1700
Data Index: 5714802 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.1000. Min Act: -0.1700
Data Index: 2339536 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0375. Min Act: -0.1700
Data Index: 6001246 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0375. Min Act: -0.1700
Data Index: 513699 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0375. Min Act: -0.1700
Data Index: 7081392 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0062. Min Act: -0.1700
Data Index: 5882669 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7562. Min Range: -8.7562
Max Act: 8.0062. Min Act: -0.1700
Data Index: 5509721 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19