Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5208 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1587. Min Range: -7.1587
Max Act: 7.1587. Min Act: -0.1700
Data Index: 7643915 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.9400. Min Act: -0.1700
Data Index: 7778013 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.9087. Min Act: -0.1700
Data Index: 2770180 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.8462. Min Act: -0.1700
Data Index: 1967990 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.6900. Min Act: -0.1700
Data Index: 149850 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.7212. Min Act: -0.1700
Data Index: 7591574 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.7212. Min Act: -0.1700
Data Index: 5073807 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.6587. Min Act: -0.1700
Data Index: 6590571 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.6275. Min Act: -0.1700
Data Index: 7811568 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5962. Min Act: -0.1700
Data Index: 5410796 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5962. Min Act: -0.1700
Data Index: 122056 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5650. Min Act: -0.1700
Data Index: 4625334 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5650. Min Act: -0.1700
Data Index: 3780681 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5337. Min Act: -0.1700
Data Index: 379664 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5337. Min Act: -0.1700
Data Index: 7196143 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5025. Min Act: -0.1700
Data Index: 7313327 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.5025. Min Act: -0.1700
Data Index: 1433139 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.3775. Min Act: -0.1700
Data Index: 7005894 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.4087. Min Act: -0.1700
Data Index: 8544569 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1587. Min Range: -7.1587
Max Act: 6.4087. Min Act: -0.1700
Data Index: 7043007 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19