Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.8211. Min Act: -0.1700
Data Index: 2804086 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.8211. Min Act: -0.1700
Data Index: 7723738 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.7899. Min Act: -0.1700
Data Index: 1077181 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.7586. Min Act: -0.1700
Data Index: 3018559 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.7586. Min Act: -0.1700
Data Index: 1248349 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 212500 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 4449235 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5711. Min Act: -0.1700
Data Index: 3879086 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5711. Min Act: -0.1700
Data Index: 5883865 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5399. Min Act: -0.1700
Data Index: 749809 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5399. Min Act: -0.1700
Data Index: 5026747 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5086. Min Act: -0.1700
Data Index: 7323980 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.5086. Min Act: -0.1700
Data Index: 2334465 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4461. Min Act: -0.1700
Data Index: 6242055 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4461. Min Act: -0.1700
Data Index: 6511740 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4461. Min Act: -0.1700
Data Index: 7170427 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4461. Min Act: -0.1700
Data Index: 7323060 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4149. Min Act: -0.1700
Data Index: 8178820 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.4149. Min Act: -0.1700
Data Index: 1521069 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8211. Min Range: -5.8211
Max Act: 5.3836. Min Act: -0.1700
Data Index: 3050812 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19