Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1441 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0688. Min Range: -11.0688
Max Act: 11.0688. Min Act: -0.1700
Data Index: 2430802 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.8813. Min Act: -0.1700
Data Index: 6938336 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.8188. Min Act: -0.1700
Data Index: 8321173 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.6938. Min Act: -0.1700
Data Index: 7998912 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.6938. Min Act: -0.1700
Data Index: 7675395 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.6938. Min Act: -0.1700
Data Index: 5837891 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5688. Min Act: -0.1700
Data Index: 31596 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5688. Min Act: -0.1700
Data Index: 500745 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.6313. Min Act: -0.1700
Data Index: 1349149 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5063. Min Act: -0.1700
Data Index: 1872733 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5063. Min Act: -0.1700
Data Index: 7950410 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5063. Min Act: -0.1700
Data Index: 4918631 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5688. Min Act: -0.1700
Data Index: 7746876 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.5063. Min Act: -0.1700
Data Index: 1522956 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.4438. Min Act: -0.1700
Data Index: 7496393 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.4438. Min Act: -0.1700
Data Index: 3063944 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.3813. Min Act: -0.1700
Data Index: 8665947 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.3813. Min Act: -0.1700
Data Index: 3937785 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.3813. Min Act: -0.1700
Data Index: 3465162 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0688. Min Range: -11.0688
Max Act: 10.3813. Min Act: -0.1700
Data Index: 7896311 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19