Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9907. Min Range: -6.9907
Max Act: 6.9907. Min Act: -0.1700
Data Index: 1159393 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4950334 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.8969. Min Act: -0.1700
Data Index: 271820 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.8344. Min Act: -0.1700
Data Index: 5921783 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.8032. Min Act: -0.1700
Data Index: 6719746 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7719. Min Act: -0.1700
Data Index: 2250223 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7407. Min Act: -0.1700
Data Index: 2245049 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7094. Min Act: -0.1700
Data Index: 8396783 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7094. Min Act: -0.1700
Data Index: 8803955 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7094. Min Act: -0.1700
Data Index: 1906737 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.7407. Min Act: -0.1700
Data Index: 2001287 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 546399 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 103179 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 7705729 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6469. Min Act: -0.1700
Data Index: 2316711 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6469. Min Act: -0.1700
Data Index: 3191723 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6469. Min Act: -0.1700
Data Index: 1531927 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6469. Min Act: -0.1700
Data Index: 8794196 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6469. Min Act: -0.1700
Data Index: 8765140 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9907. Min Range: -6.9907
Max Act: 5.6157. Min Act: -0.1700
Data Index: 2398457 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19