Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3177 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3406. Min Range: -10.3406
Max Act: 10.3406. Min Act: -0.1700
Data Index: 1454779 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3406. Min Range: -10.3406
Max Act: 10.1531. Min Act: -0.1700
Data Index: 8242754 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3406. Min Range: -10.3406
Max Act: 10.1531. Min Act: -0.1700
Data Index: 449812 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.9656. Min Act: -0.1700
Data Index: 7426759 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.9656. Min Act: -0.1700
Data Index: 8164140 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7781. Min Act: -0.1700
Data Index: 2771385 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7781. Min Act: -0.1700
Data Index: 3709782 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7156. Min Act: -0.1700
Data Index: 8261701 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7156. Min Act: -0.1700
Data Index: 7678392 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7156. Min Act: -0.1700
Data Index: 1496406 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7156. Min Act: -0.1700
Data Index: 3051303 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.7156. Min Act: -0.1700
Data Index: 2989096 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.6531. Min Act: -0.1700
Data Index: 3410583 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.6531. Min Act: -0.1700
Data Index: 7264145 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.6531. Min Act: -0.1700
Data Index: 1254082 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.5906. Min Act: -0.1700
Data Index: 3075299 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.5906. Min Act: -0.1700
Data Index: 99369 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.6531. Min Act: -0.1700
Data Index: 2953636 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.5281. Min Act: -0.1700
Data Index: 4512274 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3406. Min Range: -10.3406
Max Act: 9.5906. Min Act: -0.1700
Data Index: 449572 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19