Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.8039. Min Act: -0.1700
Data Index: 1077827 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.7414. Min Act: -0.1700
Data Index: 4547557 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.7102. Min Act: -0.1700
Data Index: 4514286 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5852. Min Act: -0.1700
Data Index: 4514285 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5852. Min Act: -0.1700
Data Index: 7173417 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5852. Min Act: -0.1700
Data Index: 2691584 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5852. Min Act: -0.1700
Data Index: 1409276 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5539. Min Act: -0.1700
Data Index: 6285485 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5227. Min Act: -0.1700
Data Index: 7947652 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5227. Min Act: -0.1700
Data Index: 8753707 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5539. Min Act: -0.1700
Data Index: 2691583 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5227. Min Act: -0.1700
Data Index: 7092607 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.5227. Min Act: -0.1700
Data Index: 8600045 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4914. Min Act: -0.1700
Data Index: 998537 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4602. Min Act: -0.1700
Data Index: 5445256 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4602. Min Act: -0.1700
Data Index: 2100011 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4602. Min Act: -0.1700
Data Index: 5242959 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4602. Min Act: -0.1700
Data Index: 789215 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.4289. Min Act: -0.1700
Data Index: 3317358 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8039. Min Range: -4.8039
Max Act: 4.3977. Min Act: -0.1700
Data Index: 7154138 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19