Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.9626. Min Act: -0.1700
Data Index: 5048144 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.9313. Min Act: -0.1700
Data Index: 4923178 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.8376. Min Act: -0.1700
Data Index: 5048146 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.6813. Min Act: -0.1700
Data Index: 6809887 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.6188. Min Act: -0.1700
Data Index: 5973489 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.5876. Min Act: -0.1700
Data Index: 6090314 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.5563. Min Act: -0.1700
Data Index: 4923184 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.5563. Min Act: -0.1700
Data Index: 1407303 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.5251. Min Act: -0.1700
Data Index: 5973490 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.4938. Min Act: -0.1700
Data Index: 6513957 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.4313. Min Act: -0.1700
Data Index: 2859835 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.4313. Min Act: -0.1700
Data Index: 3419889 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.4313. Min Act: -0.1700
Data Index: 1376369 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.4001. Min Act: -0.1700
Data Index: 1999186 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.3688. Min Act: -0.1700
Data Index: 7944525 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.3688. Min Act: -0.1700
Data Index: 7100462 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.3376. Min Act: -0.1700
Data Index: 8060876 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.2438. Min Act: -0.1700
Data Index: 973214 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.2751. Min Act: -0.1700
Data Index: 7156620 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9626. Min Range: -5.9626
Max Act: 5.2126. Min Act: -0.1700
Data Index: 3454187 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19