Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.2070. Min Act: -0.1700
Data Index: 1887050 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.2383. Min Act: -0.1700
Data Index: 8080410 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.1133. Min Act: -0.1700
Data Index: 8093416 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.0820. Min Act: -0.1700
Data Index: 440383 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.0195. Min Act: -0.1700
Data Index: 3535913 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.0195. Min Act: -0.1700
Data Index: 1510801 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2383. Min Range: -6.2383
Max Act: 6.0195. Min Act: -0.1700
Data Index: 1737552 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9570. Min Act: -0.1700
Data Index: 7384063 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9570. Min Act: -0.1700
Data Index: 6035556 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9570. Min Act: -0.1700
Data Index: 8132340 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9570. Min Act: -0.1700
Data Index: 5309552 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9258. Min Act: -0.1700
Data Index: 5406732 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.9258. Min Act: -0.1700
Data Index: 6979782 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8945. Min Act: -0.1700
Data Index: 8258143 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8945. Min Act: -0.1700
Data Index: 2378483 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8945. Min Act: -0.1700
Data Index: 8222715 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8633. Min Act: -0.1700
Data Index: 4675503 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8633. Min Act: -0.1700
Data Index: 5202915 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8320. Min Act: -0.1700
Data Index: 7615901 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2383. Min Range: -6.2383
Max Act: 5.8320. Min Act: -0.1700
Data Index: 3033835 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19