Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5021 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1741. Min Range: -4.1741
Max Act: 4.1741. Min Act: -0.1700
Data Index: 6660627 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1741. Min Range: -4.1741
Max Act: 4.1428. Min Act: -0.1700
Data Index: 46573 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1741. Min Range: -4.1741
Max Act: 4.1116. Min Act: -0.1700
Data Index: 81197 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1741. Min Range: -4.1741
Max Act: 4.0803. Min Act: -0.1700
Data Index: 5954451 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1741. Min Range: -4.1741
Max Act: 4.0491. Min Act: -0.1700
Data Index: 6313921 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.9553. Min Act: -0.1700
Data Index: 2197992 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.8928. Min Act: -0.1700
Data Index: 3855705 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.9240. Min Act: -0.1700
Data Index: 2759213 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.9240. Min Act: -0.1700
Data Index: 725852 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.9553. Min Act: -0.1700
Data Index: 81198 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.8928. Min Act: -0.1700
Data Index: 2197987 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.8928. Min Act: -0.1700
Data Index: 4891819 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.8302. Min Act: -0.1700
Data Index: 4012695 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7989. Min Act: -0.1700
Data Index: 81194 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.8302. Min Act: -0.1700
Data Index: 3079078 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7989. Min Act: -0.1700
Data Index: 3846954 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7677. Min Act: -0.1700
Data Index: 725853 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7989. Min Act: -0.1700
Data Index: 2197989 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7989. Min Act: -0.1700
Data Index: 4891820 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1741. Min Range: -4.1741
Max Act: 3.7989. Min Act: -0.1700
Data Index: 1466716 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19