Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.5178. Min Act: -0.1700
Data Index: 1575779 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4241. Min Act: -0.1700
Data Index: 7892340 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.4241. Min Act: -0.1700
Data Index: 5388333 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.3616. Min Act: -0.1700
Data Index: 3065909 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2991. Min Act: -0.1700
Data Index: 8810571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2991. Min Act: -0.1700
Data Index: 3000657 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2366. Min Act: -0.1700
Data Index: 7401064 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2678. Min Act: -0.1700
Data Index: 8763037 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2678. Min Act: -0.1700
Data Index: 4289503 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2678. Min Act: -0.1700
Data Index: 474278 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2366. Min Act: -0.1700
Data Index: 5517213 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2366. Min Act: -0.1700
Data Index: 2643237 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2053. Min Act: -0.1700
Data Index: 5954558 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.2053. Min Act: -0.1700
Data Index: 8413972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1741. Min Act: -0.1700
Data Index: 3957343 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1741. Min Act: -0.1700
Data Index: 661331 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1741. Min Act: -0.1700
Data Index: 3330578 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1428. Min Act: -0.1700
Data Index: 7178188 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1741. Min Act: -0.1700
Data Index: 6330766 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5178. Min Range: -5.5178
Max Act: 5.1741. Min Act: -0.1700
Data Index: 288093 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19