Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.2779. Min Act: -0.1700
Data Index: 2726281 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.2154. Min Act: -0.1700
Data Index: 4423880 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.1841. Min Act: -0.1700
Data Index: 8263974 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.1529. Min Act: -0.1700
Data Index: 3222168 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0904. Min Act: -0.1700
Data Index: 5066372 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0591. Min Act: -0.1700
Data Index: 4397066 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0591. Min Act: -0.1700
Data Index: 3965354 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0279. Min Act: -0.1700
Data Index: 3781525 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0279. Min Act: -0.1700
Data Index: 5835790 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0279. Min Act: -0.1700
Data Index: 661044 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2779. Min Range: -5.2779
Max Act: 5.0279. Min Act: -0.1700
Data Index: 7591440 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9966. Min Act: -0.1700
Data Index: 4423881 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9966. Min Act: -0.1700
Data Index: 3109179 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9966. Min Act: -0.1700
Data Index: 1548699 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9654. Min Act: -0.1700
Data Index: 4691260 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9654. Min Act: -0.1700
Data Index: 3426492 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9341. Min Act: -0.1700
Data Index: 7104698 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9341. Min Act: -0.1700
Data Index: 8180661 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9341. Min Act: -0.1700
Data Index: 8183693 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2779. Min Range: -5.2779
Max Act: 4.9341. Min Act: -0.1700
Data Index: 1033733 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19