Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.6866. Min Act: -0.1700
Data Index: 6154794 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.5616. Min Act: -0.1700
Data Index: 804396 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.4991. Min Act: -0.1700
Data Index: 768284 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.4366. Min Act: -0.1700
Data Index: 5689446 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.4366. Min Act: -0.1700
Data Index: 2842698 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3741. Min Act: -0.1700
Data Index: 3783077 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3741. Min Act: -0.1700
Data Index: 2407478 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3741. Min Act: -0.1700
Data Index: 3864243 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 309185 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 6718554 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 3640394 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 8288606 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 856660 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 3349079 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 8280640 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.3116. Min Act: -0.1700
Data Index: 6747849 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.2491. Min Act: -0.1700
Data Index: 3787670 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.2491. Min Act: -0.1700
Data Index: 1380971 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.2491. Min Act: -0.1700
Data Index: 5965609 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6866. Min Range: -9.6866
Max Act: 9.2491. Min Act: -0.1700
Data Index: 5355463 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19