Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.9938. Min Act: -0.1700
Data Index: 666834 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.7438. Min Act: -0.1700
Data Index: 4039006 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.6188. Min Act: -0.1700
Data Index: 3325991 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.6188. Min Act: -0.1700
Data Index: 7793383 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.6188. Min Act: -0.1700
Data Index: 7106906 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.5563. Min Act: -0.1700
Data Index: 5052364 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.4938. Min Act: -0.1700
Data Index: 4599963 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.3688. Min Act: -0.1700
Data Index: 2180189 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.3376. Min Act: -0.1700
Data Index: 1094298 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.3376. Min Act: -0.1700
Data Index: 4026387 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.3063. Min Act: -0.1700
Data Index: 7088909 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.2751. Min Act: -0.1700
Data Index: 2834836 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.2751. Min Act: -0.1700
Data Index: 6091154 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.2438. Min Act: -0.1700
Data Index: 3484206 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.1813. Min Act: -0.1700
Data Index: 4668639 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.2126. Min Act: -0.1700
Data Index: 1127242 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.1501. Min Act: -0.1700
Data Index: 3683554 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.1188. Min Act: -0.1700
Data Index: 1571881 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.0563. Min Act: -0.1700
Data Index: 1533690 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9938. Min Range: -8.9938
Max Act: 8.0876. Min Act: -0.1700
Data Index: 391412 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19