Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6052 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.3180. Min Act: -0.1700
Data Index: 5147464 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.3180. Min Act: -0.1700
Data Index: 7861351 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.1930. Min Act: -0.1700
Data Index: 3394725 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.1305. Min Act: -0.1700
Data Index: 6845219 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.0055. Min Act: -0.1700
Data Index: 1342370 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3180. Min Range: -8.3180
Max Act: 8.0055. Min Act: -0.1700
Data Index: 4066222 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.9430. Min Act: -0.1700
Data Index: 5754534 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.9430. Min Act: -0.1700
Data Index: 4458842 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.8805. Min Act: -0.1700
Data Index: 3609101 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.9430. Min Act: -0.1700
Data Index: 2886749 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.8180. Min Act: -0.1700
Data Index: 4374709 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.7555. Min Act: -0.1700
Data Index: 1312932 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.7555. Min Act: -0.1700
Data Index: 7853713 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6930. Min Act: -0.1700
Data Index: 7679775 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.8180. Min Act: -0.1700
Data Index: 3612613 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6930. Min Act: -0.1700
Data Index: 769759 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6617. Min Act: -0.1700
Data Index: 5218431 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6930. Min Act: -0.1700
Data Index: 4745761 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6617. Min Act: -0.1700
Data Index: 5141941 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3180. Min Range: -8.3180
Max Act: 7.6617. Min Act: -0.1700
Data Index: 5037247 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19