Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3260. Min Range: -8.3260
Max Act: 8.3260. Min Act: -0.1700
Data Index: 7811212 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.7635. Min Act: -0.1700
Data Index: 1127586 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.4510. Min Act: -0.1700
Data Index: 2461481 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.3260. Min Act: -0.1700
Data Index: 1509233 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.1385. Min Act: -0.1700
Data Index: 6765816 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.1385. Min Act: -0.1700
Data Index: 197568 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.1073. Min Act: -0.1700
Data Index: 1665671 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.1073. Min Act: -0.1700
Data Index: 716789 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.0760. Min Act: -0.1700
Data Index: 8261499 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.0760. Min Act: -0.1700
Data Index: 1624927 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.0760. Min Act: -0.1700
Data Index: 455411 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.0135. Min Act: -0.1700
Data Index: 6385163 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3260. Min Range: -8.3260
Max Act: 7.0135. Min Act: -0.1700
Data Index: 8129386 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.9823. Min Act: -0.1700
Data Index: 1372133 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.9823. Min Act: -0.1700
Data Index: 1859797 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.8885. Min Act: -0.1700
Data Index: 8144014 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.9198. Min Act: -0.1700
Data Index: 2460240 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.9198. Min Act: -0.1700
Data Index: 2581266 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.8885. Min Act: -0.1700
Data Index: 4281528 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3260. Min Range: -8.3260
Max Act: 6.8885. Min Act: -0.1700
Data Index: 5157166 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19