Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7955. Min Act: -0.1700
Data Index: 8390913 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7642. Min Act: -0.1700
Data Index: 1951084 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7329. Min Act: -0.1700
Data Index: 5871696 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7329. Min Act: -0.1700
Data Index: 2415297 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7017. Min Act: -0.1700
Data Index: 6518348 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.7017. Min Act: -0.1700
Data Index: 5215751 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6860. Min Act: -0.1700
Data Index: 5503408 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6704. Min Act: -0.1700
Data Index: 887250 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6391. Min Act: -0.1700
Data Index: 1806670 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6547. Min Act: -0.1700
Data Index: 6713327 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6391. Min Act: -0.1700
Data Index: 1471156 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.6078. Min Act: -0.1700
Data Index: 6584910 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5921. Min Act: -0.1700
Data Index: 7258349 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5921. Min Act: -0.1700
Data Index: 7103477 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5765. Min Act: -0.1700
Data Index: 3575360 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5608. Min Act: -0.1700
Data Index: 2411855 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5765. Min Act: -0.1700
Data Index: 2828730 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5765. Min Act: -0.1700
Data Index: 5911858 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5921. Min Act: -0.1700
Data Index: 3083252 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7955. Min Range: -3.7955
Max Act: 3.5765. Min Act: -0.1700
Data Index: 2488573 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19