Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5239 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0876. Min Range: -6.0876
Max Act: 6.0876. Min Act: -0.1700
Data Index: 839752 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.9626. Min Act: -0.1700
Data Index: 8056315 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.9001. Min Act: -0.1700
Data Index: 5475189 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.9314. Min Act: -0.1700
Data Index: 4795717 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8689. Min Act: -0.1700
Data Index: 4024794 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8376. Min Act: -0.1700
Data Index: 85641 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 8746840 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 695145 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2823463 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 8485195 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 2741628 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2642210 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 3362397 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 8766218 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 7681224 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 1450037 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 1240003 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 760506 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 1134767 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7751. Min Act: -0.1700
Data Index: 3182577 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19