Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.1705. Min Act: -0.1700
Data Index: 3482269 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.0767. Min Act: -0.1700
Data Index: 1719729 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.0455. Min Act: -0.1700
Data Index: 8594596 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.0142. Min Act: -0.1700
Data Index: 1252866 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.9517. Min Act: -0.1700
Data Index: 2452827 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.9517. Min Act: -0.1700
Data Index: 463340 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.9517. Min Act: -0.1700
Data Index: 8033698 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8892. Min Act: -0.1700
Data Index: 2737071 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8892. Min Act: -0.1700
Data Index: 7168669 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8892. Min Act: -0.1700
Data Index: 7838923 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8580. Min Act: -0.1700
Data Index: 323957 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8580. Min Act: -0.1700
Data Index: 959191 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8580. Min Act: -0.1700
Data Index: 2257198 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 2302324 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 7147523 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 5133605 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 3559199 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 4323207 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1292488 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8267. Min Act: -0.1700
Data Index: 264020 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19