Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.6893. Min Act: -0.1700
Data Index: 4663824 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.5643. Min Act: -0.1700
Data Index: 6025488 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.5643. Min Act: -0.1700
Data Index: 1078033 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.4393. Min Act: -0.1700
Data Index: 2674221 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.4393. Min Act: -0.1700
Data Index: 3358246 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.4393. Min Act: -0.1700
Data Index: 5104894 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.5018. Min Act: -0.1700
Data Index: 2097959 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 2674219 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 2240787 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 719154 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 7634790 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 316425 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 806738 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.3143. Min Act: -0.1700
Data Index: 2674214 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.2518. Min Act: -0.1700
Data Index: 8123630 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.2518. Min Act: -0.1700
Data Index: 2868137 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.1268. Min Act: -0.1700
Data Index: 5639078 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.1893. Min Act: -0.1700
Data Index: 3930827 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.1268. Min Act: -0.1700
Data Index: 1931337 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6893. Min Range: -8.6893
Max Act: 8.1268. Min Act: -0.1700
Data Index: 6517607 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19