Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.7558. Min Act: -0.1700
Data Index: 8600540 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.7245. Min Act: -0.1700
Data Index: 8600534 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.3183. Min Act: -0.1700
Data Index: 4324220 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.2870. Min Act: -0.1700
Data Index: 5570909 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.1933. Min Act: -0.1700
Data Index: 1675073 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.1620. Min Act: -0.1700
Data Index: 481044 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.1620. Min Act: -0.1700
Data Index: 3543067 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0995. Min Act: -0.1700
Data Index: 2414347 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0995. Min Act: -0.1700
Data Index: 7221683 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0058. Min Act: -0.1700
Data Index: 1670186 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0058. Min Act: -0.1700
Data Index: 3822853 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0058. Min Act: -0.1700
Data Index: 5684433 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7558. Min Range: -7.7558
Max Act: 7.0058. Min Act: -0.1700
Data Index: 4229584 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9745. Min Act: -0.1700
Data Index: 6285262 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9433. Min Act: -0.1700
Data Index: 1671183 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9120. Min Act: -0.1700
Data Index: 6051621 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.8808. Min Act: -0.1700
Data Index: 8384719 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9120. Min Act: -0.1700
Data Index: 7010844 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9120. Min Act: -0.1700
Data Index: 5097827 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7558. Min Range: -7.7558
Max Act: 6.9120. Min Act: -0.1700
Data Index: 7232373 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19