Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.6465. Min Act: -0.1700
Data Index: 3898542 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.3652. Min Act: -0.1700
Data Index: 966069 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.3340. Min Act: -0.1700
Data Index: 4344970 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.2402. Min Act: -0.1700
Data Index: 6255835 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.2715. Min Act: -0.1700
Data Index: 4214113 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.2402. Min Act: -0.1700
Data Index: 7847005 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.1777. Min Act: -0.1700
Data Index: 4842755 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.1777. Min Act: -0.1700
Data Index: 2744363 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.2090. Min Act: -0.1700
Data Index: 8269359 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.2090. Min Act: -0.1700
Data Index: 6477939 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.1152. Min Act: -0.1700
Data Index: 3830447 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.1465. Min Act: -0.1700
Data Index: 6826528 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0840. Min Act: -0.1700
Data Index: 5675225 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0840. Min Act: -0.1700
Data Index: 8605861 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0527. Min Act: -0.1700
Data Index: 1376710 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0527. Min Act: -0.1700
Data Index: 3761338 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0840. Min Act: -0.1700
Data Index: 8375265 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0840. Min Act: -0.1700
Data Index: 355359 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6465. Min Range: -7.6465
Max Act: 6.9902. Min Act: -0.1700
Data Index: 8485730 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6465. Min Range: -7.6465
Max Act: 7.0215. Min Act: -0.1700
Data Index: 3474556 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19