Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1022. Min Range: -3.1022
Max Act: 3.1022. Min Act: -0.1700
Data Index: 1158958 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1022. Min Range: -3.1022
Max Act: 3.0076. Min Act: -0.1700
Data Index: 8726395 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1022. Min Range: -3.1022
Max Act: 3.0076. Min Act: -0.1700
Data Index: 6427596 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9601. Min Act: -0.1700
Data Index: 432587 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9443. Min Act: -0.1700
Data Index: 4121757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9285. Min Act: -0.1700
Data Index: 1592729 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9126. Min Act: -0.1700
Data Index: 352232 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9285. Min Act: -0.1700
Data Index: 3156539 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9126. Min Act: -0.1700
Data Index: 937921 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9126. Min Act: -0.1700
Data Index: 3982083 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.9126. Min Act: -0.1700
Data Index: 3156538 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8968. Min Act: -0.1700
Data Index: 855695 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8968. Min Act: -0.1700
Data Index: 8358361 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8968. Min Act: -0.1700
Data Index: 5550533 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8809. Min Act: -0.1700
Data Index: 5168966 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8809. Min Act: -0.1700
Data Index: 4584411 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8809. Min Act: -0.1700
Data Index: 7247081 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8809. Min Act: -0.1700
Data Index: 5952546 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8491. Min Act: -0.1700
Data Index: 1822653 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1022. Min Range: -3.1022
Max Act: 2.8491. Min Act: -0.1700
Data Index: 466693 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19