Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.6712. Min Act: -0.1700
Data Index: 2339574 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.6400. Min Act: -0.1700
Data Index: 5744474 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.6400. Min Act: -0.1700
Data Index: 1031255 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.5462. Min Act: -0.1700
Data Index: 785220 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.4212. Min Act: -0.1700
Data Index: 696935 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.4212. Min Act: -0.1700
Data Index: 6986082 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.3587. Min Act: -0.1700
Data Index: 774052 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.3275. Min Act: -0.1700
Data Index: 1586347 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2962. Min Act: -0.1700
Data Index: 4600446 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2962. Min Act: -0.1700
Data Index: 7653373 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2962. Min Act: -0.1700
Data Index: 4038932 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 6484168 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 4732795 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 4273446 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 551234 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 6803418 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 8616072 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2025. Min Act: -0.1700
Data Index: 387025 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2025. Min Act: -0.1700
Data Index: 2924552 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6712. Min Range: -6.6712
Max Act: 6.2337. Min Act: -0.1700
Data Index: 7612328 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19