Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.5300. Min Act: -0.1700
Data Index: 6175529 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4675. Min Act: -0.1700
Data Index: 2589983 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4362. Min Act: -0.1700
Data Index: 4113270 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4362. Min Act: -0.1700
Data Index: 4006166 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4050. Min Act: -0.1700
Data Index: 3824312 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.4362. Min Act: -0.1700
Data Index: 49951 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 5304765 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3737. Min Act: -0.1700
Data Index: 139398 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3112. Min Act: -0.1700
Data Index: 6510882 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3425. Min Act: -0.1700
Data Index: 8688135 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3112. Min Act: -0.1700
Data Index: 4892609 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.3112. Min Act: -0.1700
Data Index: 1121369 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 1945896 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 8124832 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 1085665 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 35350 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2487. Min Act: -0.1700
Data Index: 6432807 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2800. Min Act: -0.1700
Data Index: 5704787 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2487. Min Act: -0.1700
Data Index: 750610 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5300. Min Range: -4.5300
Max Act: 4.2487. Min Act: -0.1700
Data Index: 4108331 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19