Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5045 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.3376. Min Act: -0.1700
Data Index: 1261889 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.2126. Min Act: -0.1700
Data Index: 852551 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.1501. Min Act: -0.1700
Data Index: 5841568 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.2126. Min Act: -0.1700
Data Index: 4911503 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.1501. Min Act: -0.1700
Data Index: 169247 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.0876. Min Act: -0.1700
Data Index: 613089 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.0251. Min Act: -0.1700
Data Index: 7046712 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 3110186 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3376. Min Range: -9.3376
Max Act: 9.0251. Min Act: -0.1700
Data Index: 5192974 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 6060314 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 6452844 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 2853896 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 3685468 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 8025211 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9001. Min Act: -0.1700
Data Index: 2873768 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9626. Min Act: -0.1700
Data Index: 1250935 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9001. Min Act: -0.1700
Data Index: 4569367 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9001. Min Act: -0.1700
Data Index: 3378462 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.9001. Min Act: -0.1700
Data Index: 762308 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3376. Min Range: -9.3376
Max Act: 8.8376. Min Act: -0.1700
Data Index: 169248 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19