Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.1524. Min Act: -0.1700
Data Index: 3191453 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.1211. Min Act: -0.1700
Data Index: 4919255 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1524. Min Range: -7.1524
Max Act: 7.1211. Min Act: -0.1700
Data Index: 4459782 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.9961. Min Act: -0.1700
Data Index: 4741061 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.9961. Min Act: -0.1700
Data Index: 2899622 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.9961. Min Act: -0.1700
Data Index: 7432620 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.8399. Min Act: -0.1700
Data Index: 7806888 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.8399. Min Act: -0.1700
Data Index: 3953855 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7461. Min Act: -0.1700
Data Index: 2796329 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7461. Min Act: -0.1700
Data Index: 8368148 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 1954240 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 7713785 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.7149. Min Act: -0.1700
Data Index: 6795742 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 8047973 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 3226836 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 2134228 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 8587652 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1493681 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6524. Min Act: -0.1700
Data Index: 4750277 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1524. Min Range: -7.1524
Max Act: 6.6836. Min Act: -0.1700
Data Index: 8620332 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19