Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2424 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.9649. Min Act: -0.1700
Data Index: 8527964 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.8711. Min Act: -0.1700
Data Index: 7135654 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.8711. Min Act: -0.1700
Data Index: 8155399 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2168172 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.8086. Min Act: -0.1700
Data Index: 4553488 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7774. Min Act: -0.1700
Data Index: 1134049 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.8399. Min Act: -0.1700
Data Index: 1742733 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7774. Min Act: -0.1700
Data Index: 3550558 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7774. Min Act: -0.1700
Data Index: 8150987 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7774. Min Act: -0.1700
Data Index: 5132520 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7461. Min Act: -0.1700
Data Index: 8565836 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7461. Min Act: -0.1700
Data Index: 6180683 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7149. Min Act: -0.1700
Data Index: 3930875 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7149. Min Act: -0.1700
Data Index: 8729412 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7149. Min Act: -0.1700
Data Index: 634891 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.6836. Min Act: -0.1700
Data Index: 4232920 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7149. Min Act: -0.1700
Data Index: 4688884 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.7149. Min Act: -0.1700
Data Index: 1655756 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.6836. Min Act: -0.1700
Data Index: 48886 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9649. Min Range: -5.9649
Max Act: 5.6836. Min Act: -0.1700
Data Index: 1444912 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19