Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0840. Min Range: -6.0840
Max Act: 6.0840. Min Act: -0.1700
Data Index: 7716958 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0840. Min Range: -6.0840
Max Act: 6.0215. Min Act: -0.1700
Data Index: 2456674 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0840. Min Range: -6.0840
Max Act: 6.0215. Min Act: -0.1700
Data Index: 3252791 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0840. Min Range: -6.0840
Max Act: 6.0215. Min Act: -0.1700
Data Index: 6085508 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.9903. Min Act: -0.1700
Data Index: 6387599 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.9590. Min Act: -0.1700
Data Index: 1040903 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.9278. Min Act: -0.1700
Data Index: 3870 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.9278. Min Act: -0.1700
Data Index: 7104686 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.8028. Min Act: -0.1700
Data Index: 500445 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.8340. Min Act: -0.1700
Data Index: 1922439 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7715. Min Act: -0.1700
Data Index: 5628944 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7715. Min Act: -0.1700
Data Index: 3704059 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7715. Min Act: -0.1700
Data Index: 3402216 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7715. Min Act: -0.1700
Data Index: 174429 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7715. Min Act: -0.1700
Data Index: 6214235 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7403. Min Act: -0.1700
Data Index: 3394178 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7090. Min Act: -0.1700
Data Index: 2769825 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7090. Min Act: -0.1700
Data Index: 6550004 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.7090. Min Act: -0.1700
Data Index: 8208754 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0840. Min Range: -6.0840
Max Act: 5.6778. Min Act: -0.1700
Data Index: 4220091 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19