Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.5720. Min Act: -0.1700
Data Index: 3278018 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.3845. Min Act: -0.1700
Data Index: 5505184 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.3845. Min Act: -0.1700
Data Index: 8230324 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.2595. Min Act: -0.1700
Data Index: 7882796 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.1970. Min Act: -0.1700
Data Index: 6949537 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.1970. Min Act: -0.1700
Data Index: 3462383 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.0720. Min Act: -0.1700
Data Index: 6538159 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5720. Min Range: -8.5720
Max Act: 8.0720. Min Act: -0.1700
Data Index: 3622461 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.9470. Min Act: -0.1700
Data Index: 6164154 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.9470. Min Act: -0.1700
Data Index: 2008704 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8845. Min Act: -0.1700
Data Index: 4349178 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8845. Min Act: -0.1700
Data Index: 1853272 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8220. Min Act: -0.1700
Data Index: 6702611 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8220. Min Act: -0.1700
Data Index: 3087467 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8220. Min Act: -0.1700
Data Index: 3894732 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.8220. Min Act: -0.1700
Data Index: 1767245 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.7595. Min Act: -0.1700
Data Index: 612921 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.7595. Min Act: -0.1700
Data Index: 7094971 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.6970. Min Act: -0.1700
Data Index: 2642303 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5720. Min Range: -8.5720
Max Act: 7.6970. Min Act: -0.1700
Data Index: 3025790 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19