Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.9779. Min Act: -0.1700
Data Index: 7582587 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.8216. Min Act: -0.1700
Data Index: 2457222 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.7904. Min Act: -0.1700
Data Index: 7644027 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.6966. Min Act: -0.1700
Data Index: 2832914 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.6029. Min Act: -0.1700
Data Index: 2816346 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.5404. Min Act: -0.1700
Data Index: 2082731 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.5404. Min Act: -0.1700
Data Index: 8335092 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.5404. Min Act: -0.1700
Data Index: 1809222 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.5091. Min Act: -0.1700
Data Index: 1780932 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.5091. Min Act: -0.1700
Data Index: 1786553 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.4779. Min Act: -0.1700
Data Index: 2580019 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.4466. Min Act: -0.1700
Data Index: 2568376 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.4154. Min Act: -0.1700
Data Index: 1406486 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.4154. Min Act: -0.1700
Data Index: 4736988 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.3529. Min Act: -0.1700
Data Index: 4679134 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.3529. Min Act: -0.1700
Data Index: 8462996 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.3529. Min Act: -0.1700
Data Index: 6007380 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.2904. Min Act: -0.1700
Data Index: 7056078 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.2904. Min Act: -0.1700
Data Index: 186802 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9779. Min Range: -7.9779
Max Act: 7.2904. Min Act: -0.1700
Data Index: 4104504 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19