Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.5356. Min Act: -0.1693
Data Index: 2648903 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3773. Min Act: -0.1700
Data Index: 141030 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3597. Min Act: -0.1700
Data Index: 8223775 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3420. Min Act: -0.1700
Data Index: 1813603 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3420. Min Act: -0.1700
Data Index: 448982 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3420. Min Act: -0.1700
Data Index: 2717105 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3420. Min Act: -0.1700
Data Index: 6534011 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2891. Min Act: -0.1700
Data Index: 3790886 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3068. Min Act: -0.1693
Data Index: 2564688 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3068. Min Act: -0.1698
Data Index: 1548080 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.3068. Min Act: -0.1697
Data Index: 4454817 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1699
Data Index: 8764562 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2891. Min Act: -0.1700
Data Index: 487415 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2891. Min Act: -0.1668
Data Index: 4623815 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2891. Min Act: -0.1700
Data Index: 1572783 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1699
Data Index: 5139122 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1700
Data Index: 52174 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1700
Data Index: 2354682 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1699
Data Index: 1029758 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5356. Min Range: -1.5356
Max Act: 1.2715. Min Act: -0.1700
Data Index: 4300327 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19