Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.6000. Min Act: -0.1700
Data Index: 5103419 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.2875. Min Act: -0.1700
Data Index: 8149356 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.2875. Min Act: -0.1700
Data Index: 3898605 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.2250. Min Act: -0.1700
Data Index: 6212403 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.1938. Min Act: -0.1700
Data Index: 707625 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.1000. Min Act: -0.1700
Data Index: 2831000 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.1000. Min Act: -0.1700
Data Index: 7568803 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0688. Min Act: -0.1700
Data Index: 6795658 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0688. Min Act: -0.1700
Data Index: 8031319 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0688. Min Act: -0.1700
Data Index: 5890861 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0375. Min Act: -0.1700
Data Index: 3108144 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0063. Min Act: -0.1700
Data Index: 7669121 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0063. Min Act: -0.1700
Data Index: 416998 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.0063. Min Act: -0.1700
Data Index: 1947044 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9750. Min Act: -0.1700
Data Index: 4131410 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9750. Min Act: -0.1700
Data Index: 4721755 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9750. Min Act: -0.1700
Data Index: 7115747 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9438. Min Act: -0.1700
Data Index: 1034371 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9125. Min Act: -0.1700
Data Index: 1608685 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9125. Min Act: -0.1700
Data Index: 5444246 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19