Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 135 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.9783. Min Act: -0.1700
Data Index: 7998912 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.9783. Min Act: -0.1700
Data Index: 7289669 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8846. Min Act: -0.1700
Data Index: 4177024 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8846. Min Act: -0.1700
Data Index: 707784 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8533. Min Act: -0.1700
Data Index: 4829737 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8533. Min Act: -0.1700
Data Index: 5836893 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8533. Min Act: -0.1700
Data Index: 7289668 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8221. Min Act: -0.1700
Data Index: 1019662 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8221. Min Act: -0.1700
Data Index: 8059495 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.8221. Min Act: -0.1700
Data Index: 1098949 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7908. Min Act: -0.1700
Data Index: 7972925 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7596. Min Act: -0.1700
Data Index: 4794721 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7908. Min Act: -0.1700
Data Index: 8827853 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7908. Min Act: -0.1700
Data Index: 6599974 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7908. Min Act: -0.1700
Data Index: 1620981 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7596. Min Act: -0.1700
Data Index: 247139 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7596. Min Act: -0.1700
Data Index: 7195402 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7596. Min Act: -0.1700
Data Index: 6959510 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7596. Min Act: -0.1700
Data Index: 6774186 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9783. Min Range: -6.9783
Max Act: 6.7908. Min Act: -0.1700
Data Index: 5199603 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19