Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 559 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.7876. Min Act: -0.1700
Data Index: 5907953 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.5689. Min Act: -0.1700
Data Index: 1825561 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.2251. Min Act: -0.1700
Data Index: 167553 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.2251. Min Act: -0.1700
Data Index: 3250938 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1939. Min Act: -0.1700
Data Index: 6968623 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1626. Min Act: -0.1700
Data Index: 5269503 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1314. Min Act: -0.1700
Data Index: 1646104 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1626. Min Act: -0.1700
Data Index: 1987000 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1314. Min Act: -0.1700
Data Index: 8568254 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1001. Min Act: -0.1700
Data Index: 4855579 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1001. Min Act: -0.1700
Data Index: 1982596 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0689. Min Act: -0.1700
Data Index: 4740484 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0689. Min Act: -0.1700
Data Index: 8321594 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.1001. Min Act: -0.1700
Data Index: 74901 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0689. Min Act: -0.1700
Data Index: 5192783 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0689. Min Act: -0.1700
Data Index: 4021071 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0689. Min Act: -0.1700
Data Index: 8372688 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 3138124 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6679464 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7876. Min Range: -5.7876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 8290835 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19