Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.4076. Min Act: -0.1700
Data Index: 7955742 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.3451. Min Act: -0.1700
Data Index: 7955743 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.1576. Min Act: -0.1700
Data Index: 7219507 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.1264. Min Act: -0.1700
Data Index: 7016305 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.0951. Min Act: -0.1700
Data Index: 1483954 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.0951. Min Act: -0.1700
Data Index: 6682176 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4076. Min Range: -8.4076
Max Act: 8.0014. Min Act: -0.1700
Data Index: 4855637 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9389. Min Act: -0.1700
Data Index: 3187841 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 1422929 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9389. Min Act: -0.1700
Data Index: 945235 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 1891092 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 7309237 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 6110081 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8451. Min Act: -0.1700
Data Index: 3319377 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8764. Min Act: -0.1700
Data Index: 1144371 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8764. Min Act: -0.1700
Data Index: 3410183 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8451. Min Act: -0.1700
Data Index: 1471822 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8451. Min Act: -0.1700
Data Index: 4012033 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8764. Min Act: -0.1700
Data Index: 8416757 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4076. Min Range: -8.4076
Max Act: 7.8139. Min Act: -0.1700
Data Index: 6704828 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19