Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4212. Min Range: -8.4212
Max Act: 8.4212. Min Act: -0.1700
Data Index: 3940516 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4212. Min Range: -8.4212
Max Act: 8.3587. Min Act: -0.1700
Data Index: 2168813 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4212. Min Range: -8.4212
Max Act: 8.1087. Min Act: -0.1700
Data Index: 7241684 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9837. Min Act: -0.1700
Data Index: 3029025 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9837. Min Act: -0.1700
Data Index: 7639180 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9212. Min Act: -0.1700
Data Index: 7570902 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9212. Min Act: -0.1700
Data Index: 800475 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9212. Min Act: -0.1700
Data Index: 1205048 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.9212. Min Act: -0.1700
Data Index: 4495542 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.8587. Min Act: -0.1700
Data Index: 5939882 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.8587. Min Act: -0.1700
Data Index: 1354371 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.8587. Min Act: -0.1700
Data Index: 2464676 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7962. Min Act: -0.1700
Data Index: 7103755 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7962. Min Act: -0.1700
Data Index: 7406617 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7962. Min Act: -0.1700
Data Index: 70402 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7337. Min Act: -0.1700
Data Index: 5128901 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7337. Min Act: -0.1700
Data Index: 8239958 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7337. Min Act: -0.1700
Data Index: 4965786 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7337. Min Act: -0.1700
Data Index: 49584 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4212. Min Range: -8.4212
Max Act: 7.7337. Min Act: -0.1700
Data Index: 7185354 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19