Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3037 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.2644. Min Act: -0.1700
Data Index: 7819794 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.2644. Min Act: -0.1700
Data Index: 8436919 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.2019. Min Act: -0.1700
Data Index: 2732458 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.2019. Min Act: -0.1700
Data Index: 2087225 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.1394. Min Act: -0.1700
Data Index: 3586294 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.1394. Min Act: -0.1700
Data Index: 5782795 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2644. Min Range: -7.2644
Max Act: 7.0769. Min Act: -0.1700
Data Index: 6221745 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.9519. Min Act: -0.1700
Data Index: 5273526 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.9207. Min Act: -0.1700
Data Index: 7500521 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8894. Min Act: -0.1700
Data Index: 3852826 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8894. Min Act: -0.1700
Data Index: 5990795 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8582. Min Act: -0.1700
Data Index: 7227183 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8269. Min Act: -0.1700
Data Index: 4774445 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8269. Min Act: -0.1700
Data Index: 1836417 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8269. Min Act: -0.1700
Data Index: 5648829 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.8582. Min Act: -0.1700
Data Index: 6564137 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.7957. Min Act: -0.1700
Data Index: 1202374 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.7957. Min Act: -0.1700
Data Index: 4007606 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.7957. Min Act: -0.1700
Data Index: 792336 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2644. Min Range: -7.2644
Max Act: 6.7644. Min Act: -0.1700
Data Index: 8475888 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19