Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0417. Min Range: -3.0417
Max Act: 3.0417. Min Act: -0.1700
Data Index: 5506039 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.9943. Min Act: -0.1700
Data Index: 5267340 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.9785. Min Act: -0.1700
Data Index: 1857041 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.9627. Min Act: -0.1700
Data Index: 3027564 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.8676. Min Act: -0.1700
Data Index: 7094452 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.8199. Min Act: -0.1700
Data Index: 6522386 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7881. Min Act: -0.1700
Data Index: 3777916 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7562. Min Act: -0.1700
Data Index: 6329793 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7402. Min Act: -0.1700
Data Index: 1862932 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7402. Min Act: -0.1700
Data Index: 406273 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7402. Min Act: -0.1700
Data Index: 6020951 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7243. Min Act: -0.1700
Data Index: 825521 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7243. Min Act: -0.1700
Data Index: 5407609 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7083. Min Act: -0.1700
Data Index: 4988433 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7083. Min Act: -0.1700
Data Index: 7612182 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.7083. Min Act: -0.1700
Data Index: 627883 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.6923. Min Act: -0.1700
Data Index: 2751866 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.6923. Min Act: -0.1700
Data Index: 6703402 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.6923. Min Act: -0.1700
Data Index: 166527 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0417. Min Range: -3.0417
Max Act: 2.6923. Min Act: -0.1700
Data Index: 5366571 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19