Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.8607. Min Act: -0.1700
Data Index: 6596147 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7982. Min Act: -0.1700
Data Index: 5208100 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7669. Min Act: -0.1700
Data Index: 8746930 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7357. Min Act: -0.1700
Data Index: 5208101 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7044. Min Act: -0.1700
Data Index: 5652280 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7044. Min Act: -0.1700
Data Index: 6596150 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6732. Min Act: -0.1700
Data Index: 1406155 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.7044. Min Act: -0.1700
Data Index: 4961297 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6419. Min Act: -0.1700
Data Index: 8648230 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6107. Min Act: -0.1700
Data Index: 7736523 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6107. Min Act: -0.1700
Data Index: 32250 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6107. Min Act: -0.1700
Data Index: 1406156 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5794. Min Act: -0.1700
Data Index: 5652278 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.6107. Min Act: -0.1700
Data Index: 5652276 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5482. Min Act: -0.1700
Data Index: 8746929 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5482. Min Act: -0.1700
Data Index: 8648229 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5482. Min Act: -0.1700
Data Index: 1406157 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5482. Min Act: -0.1700
Data Index: 5069741 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5169. Min Act: -0.1700
Data Index: 8703289 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8607. Min Range: -5.8607
Max Act: 5.5169. Min Act: -0.1700
Data Index: 6800932 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19