Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.5375. Min Act: -0.1700
Data Index: 5881477 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.5375. Min Act: -0.1700
Data Index: 43822 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.5062. Min Act: -0.1700
Data Index: 5461821 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.4437. Min Act: -0.1700
Data Index: 1828231 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.4437. Min Act: -0.1700
Data Index: 4615206 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8698981 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.4125. Min Act: -0.1700
Data Index: 3468023 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.4125. Min Act: -0.1700
Data Index: 393049 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3812. Min Act: -0.1700
Data Index: 4683607 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3500. Min Act: -0.1700
Data Index: 6301373 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3500. Min Act: -0.1700
Data Index: 2421352 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3187. Min Act: -0.1700
Data Index: 8298378 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3187. Min Act: -0.1700
Data Index: 2118016 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2875. Min Act: -0.1700
Data Index: 646946 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.3187. Min Act: -0.1700
Data Index: 2788662 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2875. Min Act: -0.1700
Data Index: 1357812 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1408377 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2562. Min Act: -0.1700
Data Index: 6923079 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2875. Min Act: -0.1700
Data Index: 6897633 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5375. Min Range: -5.5375
Max Act: 5.2562. Min Act: -0.1700
Data Index: 6293130 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19