Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.6370. Min Act: -0.1700
Data Index: 605617 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.2932. Min Act: -0.1700
Data Index: 3445012 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.1995. Min Act: -0.1700
Data Index: 529737 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.0745. Min Act: -0.1700
Data Index: 4826778 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.0432. Min Act: -0.1700
Data Index: 6767720 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6370. Min Range: -7.6370
Max Act: 7.0745. Min Act: -0.1700
Data Index: 3762842 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.9807. Min Act: -0.1700
Data Index: 3660323 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.9495. Min Act: -0.1700
Data Index: 1896901 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.8870. Min Act: -0.1700
Data Index: 6549391 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.9182. Min Act: -0.1700
Data Index: 2213748 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.8557. Min Act: -0.1700
Data Index: 7384581 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.8557. Min Act: -0.1700
Data Index: 4354934 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.8245. Min Act: -0.1700
Data Index: 548210 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.8245. Min Act: -0.1700
Data Index: 6332328 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.7932. Min Act: -0.1700
Data Index: 2945942 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 2646133 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 1501375 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 4535927 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8647706 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6370. Min Range: -7.6370
Max Act: 6.6995. Min Act: -0.1700
Data Index: 2528416 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19