Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1821. Min Range: -7.1821
Max Act: 7.1821. Min Act: -0.1700
Data Index: 8233907 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1821. Min Range: -7.1821
Max Act: 7.0571. Min Act: -0.1700
Data Index: 4777061 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.9634. Min Act: -0.1700
Data Index: 8446461 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.9634. Min Act: -0.1700
Data Index: 6587882 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.9009. Min Act: -0.1700
Data Index: 4266818 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8696. Min Act: -0.1700
Data Index: 7792171 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8696. Min Act: -0.1700
Data Index: 2570370 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8384. Min Act: -0.1700
Data Index: 1614292 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8384. Min Act: -0.1700
Data Index: 409967 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8384. Min Act: -0.1700
Data Index: 5184060 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 5313547 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.8071. Min Act: -0.1700
Data Index: 2912986 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.7446. Min Act: -0.1700
Data Index: 2668913 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.7446. Min Act: -0.1700
Data Index: 1091297 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.7134. Min Act: -0.1700
Data Index: 4732416 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.6821. Min Act: -0.1700
Data Index: 8708570 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.7134. Min Act: -0.1700
Data Index: 1314630 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.6821. Min Act: -0.1700
Data Index: 6401698 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.6821. Min Act: -0.1700
Data Index: 4987282 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1821. Min Range: -7.1821
Max Act: 6.6821. Min Act: -0.1700
Data Index: 1282015 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19