Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.4907. Min Act: -0.1700
Data Index: 671671 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.2407. Min Act: -0.1700
Data Index: 4385027 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.2407. Min Act: -0.1700
Data Index: 535761 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.2407. Min Act: -0.1700
Data Index: 8637907 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1782. Min Act: -0.1700
Data Index: 7813884 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1782. Min Act: -0.1700
Data Index: 5159254 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1782. Min Act: -0.1700
Data Index: 2988367 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1782. Min Act: -0.1700
Data Index: 1556704 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1782. Min Act: -0.1700
Data Index: 2783052 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.1157. Min Act: -0.1700
Data Index: 6240652 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.0532. Min Act: -0.1700
Data Index: 1475415 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.0532. Min Act: -0.1700
Data Index: 4704672 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.0532. Min Act: -0.1700
Data Index: 2427959 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4907. Min Range: -9.4907
Max Act: 9.0532. Min Act: -0.1700
Data Index: 1845407 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9907. Min Act: -0.1700
Data Index: 8784751 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9907. Min Act: -0.1700
Data Index: 1231892 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9907. Min Act: -0.1700
Data Index: 930775 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9907. Min Act: -0.1700
Data Index: 5393873 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9282. Min Act: -0.1700
Data Index: 2981059 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4907. Min Range: -9.4907
Max Act: 8.9282. Min Act: -0.1700
Data Index: 4721399 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19