Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.6211. Min Act: -0.1700
Data Index: 318041 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.3711. Min Act: -0.1700
Data Index: 7969812 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.3399. Min Act: -0.1700
Data Index: 1554222 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1282899 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.3399. Min Act: -0.1700
Data Index: 8046793 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.3086. Min Act: -0.1700
Data Index: 3092601 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.2773. Min Act: -0.1700
Data Index: 2827694 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.2461. Min Act: -0.1700
Data Index: 7810193 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.2461. Min Act: -0.1700
Data Index: 5887870 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.2461. Min Act: -0.1700
Data Index: 2192693 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1836. Min Act: -0.1700
Data Index: 4088995 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1836. Min Act: -0.1700
Data Index: 4816425 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1836. Min Act: -0.1700
Data Index: 1723363 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1836. Min Act: -0.1700
Data Index: 718733 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 5728770 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 5600790 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 1938669 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 2376917 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 6774302 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6211. Min Range: -4.6211
Max Act: 4.1523. Min Act: -0.1700
Data Index: 6375814 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19