Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0720. Min Range: -6.0720
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2008315 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0720. Min Range: -6.0720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 7002609 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0720. Min Range: -6.0720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 785620 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.9782. Min Act: -0.1700
Data Index: 2843542 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.9470. Min Act: -0.1700
Data Index: 5724893 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.9470. Min Act: -0.1700
Data Index: 7454731 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.9470. Min Act: -0.1700
Data Index: 724786 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.9157. Min Act: -0.1700
Data Index: 264538 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.8845. Min Act: -0.1700
Data Index: 6843515 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.8845. Min Act: -0.1700
Data Index: 6499571 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.8845. Min Act: -0.1700
Data Index: 1081991 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7907. Min Act: -0.1700
Data Index: 8698688 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7907. Min Act: -0.1700
Data Index: 3661104 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7595. Min Act: -0.1700
Data Index: 3778045 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7595. Min Act: -0.1700
Data Index: 2262463 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7813635 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7282. Min Act: -0.1700
Data Index: 8330444 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7282. Min Act: -0.1700
Data Index: 3879172 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.7282. Min Act: -0.1700
Data Index: 7034021 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0720. Min Range: -6.0720
Max Act: 5.6970. Min Act: -0.1700
Data Index: 1746792 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19