Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0379. Min Range: -10.0379
Max Act: 10.0379. Min Act: -0.1700
Data Index: 2746898 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.9129. Min Act: -0.1699
Data Index: 4074666 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.9129. Min Act: -0.1700
Data Index: 2658173 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.8504. Min Act: -0.1700
Data Index: 7524673 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.8504. Min Act: -0.1700
Data Index: 1527647 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 868385 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 709548 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 5886752 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 1792947 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 4179004 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 8639725 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.7254. Min Act: -0.1700
Data Index: 1477938 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6629. Min Act: -0.1700
Data Index: 6961463 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6629. Min Act: -0.1700
Data Index: 7081895 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6629. Min Act: -0.1700
Data Index: 3224484 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6629. Min Act: -0.1700
Data Index: 4077199 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6629. Min Act: -0.1700
Data Index: 5399952 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6004. Min Act: -0.1700
Data Index: 6607951 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.6004. Min Act: -0.1700
Data Index: 2380686 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0379. Min Range: -10.0379
Max Act: 9.4754. Min Act: -0.1700
Data Index: 2503264 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19