Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1433. Min Range: -7.1433
Max Act: 7.1433. Min Act: -0.1700
Data Index: 3030299 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.9558. Min Act: -0.1700
Data Index: 778667 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.9246. Min Act: -0.1700
Data Index: 2947516 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.9246. Min Act: -0.1700
Data Index: 8732745 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.9246. Min Act: -0.1700
Data Index: 4263575 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.9246. Min Act: -0.1700
Data Index: 2966333 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 630090 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8933. Min Act: -0.1700
Data Index: 3237166 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8933. Min Act: -0.1700
Data Index: 1204280 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 5845836 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8175549 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 7906909 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 7856209 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 1851792 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 1938872 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 5345215 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 1809894 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8621. Min Act: -0.1700
Data Index: 4841480 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 1947332 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1433. Min Range: -7.1433
Max Act: 6.8308. Min Act: -0.1700
Data Index: 4778152 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19