Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.8939. Min Act: -0.1700
Data Index: 3190164 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.8314. Min Act: -0.1700
Data Index: 7685701 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.7689. Min Act: -0.1700
Data Index: 6359866 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.6751. Min Act: -0.1700
Data Index: 6359864 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.6439. Min Act: -0.1700
Data Index: 4295469 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.6126. Min Act: -0.1700
Data Index: 446273 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5501. Min Act: -0.1700
Data Index: 4152478 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5501. Min Act: -0.1700
Data Index: 5314135 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5501. Min Act: -0.1700
Data Index: 7105653 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5501. Min Act: -0.1700
Data Index: 2171037 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5501. Min Act: -0.1700
Data Index: 7395890 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 212017 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 7786709 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 7609164 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 7471815 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 3887978 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 5314131 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 6510855 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 4152481 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8939. Min Range: -4.8939
Max Act: 4.5189. Min Act: -0.1700
Data Index: 1268518 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19