Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0980. Min Range: -8.0980
Max Act: 8.0980. Min Act: -0.1700
Data Index: 7925231 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.7542. Min Act: -0.1700
Data Index: 6701194 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.6292. Min Act: -0.1700
Data Index: 1817226 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.5042. Min Act: -0.1700
Data Index: 5151623 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.4417. Min Act: -0.1700
Data Index: 1729931 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.3792. Min Act: -0.1700
Data Index: 6871863 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.3480. Min Act: -0.1700
Data Index: 1796590 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.3480. Min Act: -0.1700
Data Index: 707876 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.2855. Min Act: -0.1700
Data Index: 571275 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.2230. Min Act: -0.1700
Data Index: 984695 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.1917. Min Act: -0.1700
Data Index: 1729932 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.1605. Min Act: -0.1700
Data Index: 90011 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.1292. Min Act: -0.1700
Data Index: 1946204 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0980. Min Act: -0.1700
Data Index: 1796463 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0667. Min Act: -0.1700
Data Index: 7994500 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0980. Min Act: -0.1700
Data Index: 443201 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0667. Min Act: -0.1700
Data Index: 1834046 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0667. Min Act: -0.1700
Data Index: 5329914 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0355. Min Act: -0.1700
Data Index: 858633 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0980. Min Range: -8.0980
Max Act: 7.0355. Min Act: -0.1700
Data Index: 3944614 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19