Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1055. Min Range: -8.1055
Max Act: 8.1055. Min Act: -0.1700
Data Index: 593910 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1055. Min Range: -8.1055
Max Act: 8.0430. Min Act: -0.1700
Data Index: 3546090 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.9180. Min Act: -0.1700
Data Index: 7187224 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.9180. Min Act: -0.1700
Data Index: 2845749 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.7305. Min Act: -0.1700
Data Index: 5906231 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.7305. Min Act: -0.1700
Data Index: 1131961 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.6055. Min Act: -0.1700
Data Index: 1400386 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.6367. Min Act: -0.1700
Data Index: 7338750 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.6055. Min Act: -0.1700
Data Index: 1251558 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.5742. Min Act: -0.1700
Data Index: 5166504 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.5742. Min Act: -0.1700
Data Index: 6002578 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.5742. Min Act: -0.1700
Data Index: 2067029 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.5742. Min Act: -0.1700
Data Index: 5665575 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.5117. Min Act: -0.1700
Data Index: 952442 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4805. Min Act: -0.1700
Data Index: 7786647 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4805. Min Act: -0.1700
Data Index: 790463 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4805. Min Act: -0.1700
Data Index: 4546779 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4805. Min Act: -0.1700
Data Index: 3697337 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4492. Min Act: -0.1700
Data Index: 1355416 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1055. Min Range: -8.1055
Max Act: 7.4805. Min Act: -0.1700
Data Index: 638247 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19