Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5973 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.5380. Min Act: -0.1700
Data Index: 4315287 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.5693. Min Act: -0.1700
Data Index: 7832347 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.5068. Min Act: -0.1700
Data Index: 6192077 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.5068. Min Act: -0.1700
Data Index: 2217191 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.4755. Min Act: -0.1700
Data Index: 1621488 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.4443. Min Act: -0.1700
Data Index: 93965 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.4443. Min Act: -0.1700
Data Index: 7322331 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.4130. Min Act: -0.1700
Data Index: 4979696 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.4130. Min Act: -0.1700
Data Index: 5717374 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 4652554 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5068687 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3505. Min Act: -0.1700
Data Index: 1343885 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5130889 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 4692698 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 2315168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3818. Min Act: -0.1700
Data Index: 7604495 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3505. Min Act: -0.1700
Data Index: 5807974 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7639691 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7755993 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5693. Min Range: -5.5693
Max Act: 5.3505. Min Act: -0.1700
Data Index: 2531303 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19