Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.7808. Min Act: -0.1700
Data Index: 1571385 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.6558. Min Act: -0.1700
Data Index: 2918942 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.6558. Min Act: -0.1700
Data Index: 3154630 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.4683. Min Act: -0.1700
Data Index: 5517795 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.4370. Min Act: -0.1700
Data Index: 4368997 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.3433. Min Act: -0.1700
Data Index: 4679481 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.3120. Min Act: -0.1700
Data Index: 4190004 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2808. Min Act: -0.1700
Data Index: 2032401 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2495. Min Act: -0.1700
Data Index: 1484921 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2808. Min Act: -0.1700
Data Index: 3284998 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.3120. Min Act: -0.1700
Data Index: 2178585 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2495. Min Act: -0.1700
Data Index: 6222763 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2495. Min Act: -0.1700
Data Index: 7136791 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2495. Min Act: -0.1700
Data Index: 6385163 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2183. Min Act: -0.1700
Data Index: 6437975 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2495. Min Act: -0.1700
Data Index: 56133 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2183. Min Act: -0.1700
Data Index: 1861321 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.2183. Min Act: -0.1700
Data Index: 3680912 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.1870. Min Act: -0.1700
Data Index: 653610 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7808. Min Range: -7.7808
Max Act: 7.1870. Min Act: -0.1700
Data Index: 1022824 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19