Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.3383. Min Act: -0.1700
Data Index: 7614486 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.3383. Min Act: -0.1700
Data Index: 4638797 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.3383. Min Act: -0.1700
Data Index: 5818066 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.2758. Min Act: -0.1700
Data Index: 6580463 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.2133. Min Act: -0.1700
Data Index: 1779509 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.2133. Min Act: -0.1700
Data Index: 3241641 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1820. Min Act: -0.1700
Data Index: 8335944 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1820. Min Act: -0.1700
Data Index: 844013 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 8070003 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 8083415 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 5352087 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 8414572 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 1529267 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1508. Min Act: -0.1700
Data Index: 2721639 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.0883. Min Act: -0.1700
Data Index: 7833330 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1195. Min Act: -0.1700
Data Index: 3547786 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1195. Min Act: -0.1700
Data Index: 2639874 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.1195. Min Act: -0.1700
Data Index: 7380932 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.0883. Min Act: -0.1700
Data Index: 5414144 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3383. Min Range: -5.3383
Max Act: 5.0883. Min Act: -0.1700
Data Index: 3585000 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19