Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.3827. Min Act: -0.1700
Data Index: 1322828 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.2890. Min Act: -0.1700
Data Index: 1664491 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.1640. Min Act: -0.1700
Data Index: 6321186 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.1015. Min Act: -0.1700
Data Index: 739901 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.1327. Min Act: -0.1700
Data Index: 6965948 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0390. Min Act: -0.1700
Data Index: 6427949 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0390. Min Act: -0.1700
Data Index: 4285039 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0390. Min Act: -0.1700
Data Index: 8395500 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0077. Min Act: -0.1700
Data Index: 5172542 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0390. Min Act: -0.1700
Data Index: 7772582 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0077. Min Act: -0.1700
Data Index: 5643345 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1953319 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3827. Min Range: -6.3827
Max Act: 6.0077. Min Act: -0.1700
Data Index: 3994169 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.9765. Min Act: -0.1700
Data Index: 6191572 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.9140. Min Act: -0.1700
Data Index: 7708424 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.9452. Min Act: -0.1700
Data Index: 8708808 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.9140. Min Act: -0.1700
Data Index: 8815355 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.8827. Min Act: -0.1700
Data Index: 8311133 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.8827. Min Act: -0.1700
Data Index: 6387626 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3827. Min Range: -6.3827
Max Act: 5.8827. Min Act: -0.1700
Data Index: 4738570 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19