Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.5778. Min Act: -0.1700
Data Index: 5030669 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.4840. Min Act: -0.1700
Data Index: 5760353 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.4528. Min Act: -0.1700
Data Index: 3197556 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.3590. Min Act: -0.1700
Data Index: 7325951 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.3278. Min Act: -0.1700
Data Index: 1279450 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.2653. Min Act: -0.1700
Data Index: 548114 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.2965. Min Act: -0.1700
Data Index: 15372 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.2340. Min Act: -0.1700
Data Index: 3278742 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.2340. Min Act: -0.1700
Data Index: 8380940 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.1403. Min Act: -0.1700
Data Index: 7176343 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.1403. Min Act: -0.1700
Data Index: 114195 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.1715. Min Act: -0.1700
Data Index: 8356552 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5778. Min Range: -7.5778
Max Act: 7.0153. Min Act: -0.1700
Data Index: 8427463 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9840. Min Act: -0.1700
Data Index: 2808497 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9528. Min Act: -0.1700
Data Index: 3377433 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9528. Min Act: -0.1700
Data Index: 3188843 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9528. Min Act: -0.1700
Data Index: 1268788 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9215. Min Act: -0.1700
Data Index: 4746350 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.9215. Min Act: -0.1700
Data Index: 664077 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5778. Min Range: -7.5778
Max Act: 6.8590. Min Act: -0.1700
Data Index: 1642167 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19