Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5123 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.5607. Min Act: -0.1700
Data Index: 8115177 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.1544. Min Act: -0.1700
Data Index: 5606027 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.0294. Min Act: -0.1700
Data Index: 1894013 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5607. Min Range: -5.5607
Max Act: 5.0294. Min Act: -0.1700
Data Index: 5739978 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 1966939 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 7766938 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 3895287 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4726681 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 6746961 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 714598 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9982. Min Act: -0.1700
Data Index: 7314949 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 5343475 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 8297803 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 3310430 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 8225275 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 2271257 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 4728489 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9669. Min Act: -0.1700
Data Index: 7994586 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 1845860 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5607. Min Range: -5.5607
Max Act: 4.9357. Min Act: -0.1700
Data Index: 2996251 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19