Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9747. Min Act: -0.1700
Data Index: 3147269 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9434. Min Act: -0.1700
Data Index: 531984 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9434. Min Act: -0.1700
Data Index: 6040185 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 3522388 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 4257199 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8184. Min Act: -0.1700
Data Index: 6150983 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.7559. Min Act: -0.1700
Data Index: 4840019 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.7247. Min Act: -0.1700
Data Index: 4293671 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.6934. Min Act: -0.1700
Data Index: 4781121 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.6934. Min Act: -0.1700
Data Index: 7198188 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.6309. Min Act: -0.1700
Data Index: 7767285 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.6309. Min Act: -0.1700
Data Index: 2997870 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.6309. Min Act: -0.1700
Data Index: 8279747 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5997. Min Act: -0.1700
Data Index: 4002320 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5684. Min Act: -0.1700
Data Index: 8453183 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5997. Min Act: -0.1700
Data Index: 1780702 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5997. Min Act: -0.1700
Data Index: 6756891 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5684. Min Act: -0.1700
Data Index: 2187929 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5684. Min Act: -0.1700
Data Index: 1343822 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.5684. Min Act: -0.1700
Data Index: 508739 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19