Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1499. Min Range: -6.1499
Max Act: 6.1499. Min Act: -0.1700
Data Index: 7426685 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1499. Min Range: -6.1499
Max Act: 6.0874. Min Act: -0.1700
Data Index: 4012386 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.9624. Min Act: -0.1700
Data Index: 7979446 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2825172 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.9312. Min Act: -0.1700
Data Index: 1416109 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.8687. Min Act: -0.1700
Data Index: 5247223 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.8687. Min Act: -0.1700
Data Index: 8502245 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.8374. Min Act: -0.1700
Data Index: 4863137 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.7749. Min Act: -0.1700
Data Index: 5387066 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.7437. Min Act: -0.1700
Data Index: 3571459 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.7437. Min Act: -0.1700
Data Index: 8570132 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6812. Min Act: -0.1700
Data Index: 548023 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.7124. Min Act: -0.1700
Data Index: 2409820 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.7124. Min Act: -0.1700
Data Index: 4524239 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6812. Min Act: -0.1700
Data Index: 3816478 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6812. Min Act: -0.1700
Data Index: 4190917 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6812. Min Act: -0.1700
Data Index: 1532319 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6499. Min Act: -0.1700
Data Index: 6016961 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6499. Min Act: -0.1700
Data Index: 5565493 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1499. Min Range: -6.1499
Max Act: 5.6187. Min Act: -0.1700
Data Index: 143625 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19