Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.3108. Min Act: -0.1700
Data Index: 1811637 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.2483. Min Act: -0.1700
Data Index: 8299785 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.2483. Min Act: -0.1700
Data Index: 7420385 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.1858. Min Act: -0.1700
Data Index: 2048843 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.1545. Min Act: -0.1700
Data Index: 1556430 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.1233. Min Act: -0.1700
Data Index: 8754951 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0920. Min Act: -0.1700
Data Index: 7238373 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0920. Min Act: -0.1700
Data Index: 1332753 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0920. Min Act: -0.1700
Data Index: 3940631 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0608. Min Act: -0.1700
Data Index: 7068108 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0608. Min Act: -0.1700
Data Index: 3118769 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0920. Min Act: -0.1700
Data Index: 3178792 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 417476 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 8776182 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 998833 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 6101047 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 555389 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3108. Min Range: -6.3108
Max Act: 6.0295. Min Act: -0.1700
Data Index: 7478704 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3108. Min Range: -6.3108
Max Act: 5.9983. Min Act: -0.1700
Data Index: 1028109 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3108. Min Range: -6.3108
Max Act: 5.9983. Min Act: -0.1700
Data Index: 5712864 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19