Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1421. Min Range: -3.1421
Max Act: 3.1421. Min Act: -0.1700
Data Index: 2577414 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1421. Min Range: -3.1421
Max Act: 3.0001. Min Act: -0.1700
Data Index: 1104507 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1421. Min Range: -3.1421
Max Act: 3.0001. Min Act: -0.1700
Data Index: 4774190 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9843. Min Act: -0.1700
Data Index: 3808139 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9843. Min Act: -0.1700
Data Index: 7242520 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9369. Min Act: -0.1700
Data Index: 4613288 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9369. Min Act: -0.1700
Data Index: 3128671 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9369. Min Act: -0.1700
Data Index: 6227447 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.9052. Min Act: -0.1700
Data Index: 4082677 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8893. Min Act: -0.1700
Data Index: 6793779 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8893. Min Act: -0.1700
Data Index: 410437 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8575. Min Act: -0.1700
Data Index: 1381909 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8575. Min Act: -0.1700
Data Index: 2821070 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8417. Min Act: -0.1700
Data Index: 2760523 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8258. Min Act: -0.1700
Data Index: 1702907 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8417. Min Act: -0.1700
Data Index: 5788057 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8258. Min Act: -0.1700
Data Index: 3195349 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8258. Min Act: -0.1700
Data Index: 2077187 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8098. Min Act: -0.1700
Data Index: 6038526 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1421. Min Range: -3.1421
Max Act: 2.8258. Min Act: -0.1700
Data Index: 503984 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19