Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.6649. Min Act: -0.1700
Data Index: 191656 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.7274. Min Act: -0.1700
Data Index: 1431410 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.4774. Min Act: -0.1700
Data Index: 8823305 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.4774. Min Act: -0.1700
Data Index: 2378577 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.3524. Min Act: -0.1700
Data Index: 2818604 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.3211. Min Act: -0.1700
Data Index: 473916 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.2899. Min Act: -0.1700
Data Index: 5252874 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.2899. Min Act: -0.1700
Data Index: 8492144 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.1961. Min Act: -0.1700
Data Index: 577602 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0711. Min Act: -0.1700
Data Index: 5543151 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0399. Min Act: -0.1700
Data Index: 4141286 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0086. Min Act: -0.1700
Data Index: 5256116 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0086. Min Act: -0.1700
Data Index: 5265480 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0086. Min Act: -0.1700
Data Index: 531609 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7274. Min Range: -7.7274
Max Act: 6.9774. Min Act: -0.1700
Data Index: 3558127 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7274. Min Range: -7.7274
Max Act: 6.9461. Min Act: -0.1700
Data Index: 8792752 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7274. Min Range: -7.7274
Max Act: 7.0086. Min Act: -0.1700
Data Index: 13953 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7274. Min Range: -7.7274
Max Act: 6.9461. Min Act: -0.1700
Data Index: 5134147 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7274. Min Range: -7.7274
Max Act: 6.9461. Min Act: -0.1700
Data Index: 6956212 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7274. Min Range: -7.7274
Max Act: 6.9149. Min Act: -0.1700
Data Index: 2461340 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19