Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2048062 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.6973. Min Act: -0.1700
Data Index: 2729075 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.4785. Min Act: -0.1700
Data Index: 1044922 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.4160. Min Act: -0.1700
Data Index: 1345435 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.4160. Min Act: -0.1700
Data Index: 3344889 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.4160. Min Act: -0.1700
Data Index: 7778616 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.3223. Min Act: -0.1700
Data Index: 2984948 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.2910. Min Act: -0.1700
Data Index: 7341717 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.2285. Min Act: -0.1700
Data Index: 291778 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1973. Min Act: -0.1700
Data Index: 774265 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1973. Min Act: -0.1700
Data Index: 304574 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1973. Min Act: -0.1700
Data Index: 5606750 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1660. Min Act: -0.1700
Data Index: 7016792 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1660. Min Act: -0.1700
Data Index: 4030594 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1660. Min Act: -0.1700
Data Index: 1765528 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1348. Min Act: -0.1700
Data Index: 6878187 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1348. Min Act: -0.1700
Data Index: 3974379 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1035. Min Act: -0.1700
Data Index: 1288100 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1035. Min Act: -0.1700
Data Index: 2904105 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7910. Min Range: -6.7910
Max Act: 6.1035. Min Act: -0.1700
Data Index: 6879869 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19