Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.9770. Min Range: -17.9770
Max Act: 17.9770. Min Act: -0.1700
Data Index: 2138385 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.9770. Min Range: -17.9770
Max Act: 17.4770. Min Act: -0.1700
Data Index: 701921 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.8520. Min Act: -0.1700
Data Index: 5723678 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.8520. Min Act: -0.1700
Data Index: 7507432 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.7270. Min Act: -0.1700
Data Index: 2068633 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.6020. Min Act: -0.1700
Data Index: 3324987 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.6020. Min Act: -0.1700
Data Index: 2138390 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.6020. Min Act: -0.1700
Data Index: 2941562 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 2271583 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.4770. Min Act: -0.1700
Data Index: 6639377 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 5372805 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 4003064 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 8218663 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.2270. Min Act: -0.1696
Data Index: 7726363 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 5211378 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 5001014 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.3520. Min Act: -0.1700
Data Index: 7366856 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.2270. Min Act: -0.1700
Data Index: 2973624 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.2270. Min Act: -0.1700
Data Index: 5498755 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.9770. Min Range: -17.9770
Max Act: 16.2270. Min Act: -0.1700
Data Index: 2375525 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19