Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.1103. Min Act: -0.1700
Data Index: 567614 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0945. Min Act: -0.1700
Data Index: 5818052 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0787. Min Act: -0.1700
Data Index: 4999004 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0630. Min Act: -0.1700
Data Index: 558359 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0630. Min Act: -0.1700
Data Index: 1068852 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0314. Min Act: -0.1700
Data Index: 7365173 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0314. Min Act: -0.1700
Data Index: 5075202 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 673690 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 5236535 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 1149748 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 7494869 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 4447773 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1103. Min Range: -3.1103
Max Act: 3.0156. Min Act: -0.1700
Data Index: 4624323 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9998. Min Act: -0.1700
Data Index: 1528983 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9998. Min Act: -0.1700
Data Index: 3850122 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9840. Min Act: -0.1700
Data Index: 4163234 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9840. Min Act: -0.1700
Data Index: 5454351 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9840. Min Act: -0.1700
Data Index: 2078316 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9998. Min Act: -0.1700
Data Index: 3893198 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1103. Min Range: -3.1103
Max Act: 2.9840. Min Act: -0.1700
Data Index: 5975872 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19