Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5866 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2353. Min Range: -7.2353
Max Act: 7.2353. Min Act: -0.1700
Data Index: 5143127 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2353. Min Range: -7.2353
Max Act: 7.2040. Min Act: -0.1700
Data Index: 3503570 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2353. Min Range: -7.2353
Max Act: 7.1728. Min Act: -0.1700
Data Index: 1573483 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.9228. Min Act: -0.1700
Data Index: 5512766 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.8603. Min Act: -0.1700
Data Index: 3107050 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.8915. Min Act: -0.1700
Data Index: 4262598 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.8915. Min Act: -0.1700
Data Index: 5548570 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.8603. Min Act: -0.1700
Data Index: 5223927 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.8290. Min Act: -0.1700
Data Index: 7435674 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7978. Min Act: -0.1700
Data Index: 6998951 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7665. Min Act: -0.1700
Data Index: 1175158 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7353. Min Act: -0.1700
Data Index: 5912702 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7040. Min Act: -0.1700
Data Index: 6231290 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7353. Min Act: -0.1700
Data Index: 8002639 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.7040. Min Act: -0.1700
Data Index: 906785 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.6728. Min Act: -0.1700
Data Index: 4939663 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.6728. Min Act: -0.1700
Data Index: 5387926 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.6728. Min Act: -0.1700
Data Index: 7777382 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.6415. Min Act: -0.1700
Data Index: 4544908 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2353. Min Range: -7.2353
Max Act: 6.6415. Min Act: -0.1700
Data Index: 4804102 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19