Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.1405. Min Act: -0.1700
Data Index: 5511861 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.1718. Min Act: -0.1700
Data Index: 2355392 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1718. Min Range: -6.1718
Max Act: 6.0468. Min Act: -0.1700
Data Index: 4652230 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.9530. Min Act: -0.1700
Data Index: 7684189 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8905. Min Act: -0.1700
Data Index: 7712699 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8905. Min Act: -0.1700
Data Index: 2887045 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 6710626 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 3839945 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 634856 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 137126 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 6512980 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7968. Min Act: -0.1700
Data Index: 893989 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 1003225 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 2697769 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.8280. Min Act: -0.1700
Data Index: 1014018 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 748317 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 2697770 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 5927446 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 1710527 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1718. Min Range: -6.1718
Max Act: 5.7655. Min Act: -0.1700
Data Index: 1923471 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19