Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.4634. Min Act: -0.1700
Data Index: 7288656 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.4009. Min Act: -0.1700
Data Index: 1882749 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.1509. Min Act: -0.1700
Data Index: 6041833 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.1509. Min Act: -0.1700
Data Index: 6680153 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0884. Min Act: -0.1700
Data Index: 507455 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0884. Min Act: -0.1700
Data Index: 4169786 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0884. Min Act: -0.1700
Data Index: 4188371 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0259. Min Act: -0.1700
Data Index: 655704 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0259. Min Act: -0.1700
Data Index: 4461276 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9634. Min Act: -0.1700
Data Index: 2597234 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4634. Min Range: -9.4634
Max Act: 9.0259. Min Act: -0.1700
Data Index: 6719233 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9634. Min Act: -0.1700
Data Index: 1567890 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9009. Min Act: -0.1700
Data Index: 6132114 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9009. Min Act: -0.1700
Data Index: 2951497 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9009. Min Act: -0.1700
Data Index: 300476 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9009. Min Act: -0.1700
Data Index: 2424639 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9009. Min Act: -0.1700
Data Index: 2381891 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.9634. Min Act: -0.1700
Data Index: 5709655 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.8384. Min Act: -0.1700
Data Index: 1913979 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4634. Min Range: -9.4634
Max Act: 8.8384. Min Act: -0.1700
Data Index: 5017009 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19