Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4266. Min Range: -7.4266
Max Act: 7.4266. Min Act: -0.1700
Data Index: 8025224 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4266. Min Range: -7.4266
Max Act: 7.3329. Min Act: -0.1700
Data Index: 286176 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4266. Min Range: -7.4266
Max Act: 7.1141. Min Act: -0.1700
Data Index: 6037126 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4266. Min Range: -7.4266
Max Act: 7.0829. Min Act: -0.1700
Data Index: 6852447 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4266. Min Range: -7.4266
Max Act: 7.0829. Min Act: -0.1700
Data Index: 8674266 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.9579. Min Act: -0.1700
Data Index: 3980847 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.9579. Min Act: -0.1700
Data Index: 8663286 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.8329. Min Act: -0.1700
Data Index: 5125506 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.8329. Min Act: -0.1700
Data Index: 7435115 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.8329. Min Act: -0.1700
Data Index: 705019 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7704. Min Act: -0.1700
Data Index: 7864769 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7704. Min Act: -0.1700
Data Index: 484447 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7704. Min Act: -0.1700
Data Index: 8730525 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7079. Min Act: -0.1700
Data Index: 1635756 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7391. Min Act: -0.1700
Data Index: 960335 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7391. Min Act: -0.1700
Data Index: 7689510 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7391. Min Act: -0.1700
Data Index: 637838 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7079. Min Act: -0.1700
Data Index: 3045301 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.7391. Min Act: -0.1700
Data Index: 1069515 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4266. Min Range: -7.4266
Max Act: 6.6766. Min Act: -0.1700
Data Index: 3431147 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19