Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.8895. Min Act: -0.1700
Data Index: 5265018 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.7333. Min Act: -0.1700
Data Index: 3169231 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.7333. Min Act: -0.1700
Data Index: 300564 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.6395. Min Act: -0.1700
Data Index: 1575488 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.6395. Min Act: -0.1700
Data Index: 6629563 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.6395. Min Act: -0.1700
Data Index: 6968537 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.5458. Min Act: -0.1700
Data Index: 939504 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.5458. Min Act: -0.1700
Data Index: 6275008 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.5145. Min Act: -0.1700
Data Index: 5605403 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4833. Min Act: -0.1700
Data Index: 5855158 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4833. Min Act: -0.1700
Data Index: 6262720 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.5145. Min Act: -0.1700
Data Index: 8071688 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4833. Min Act: -0.1700
Data Index: 3705846 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4520. Min Act: -0.1700
Data Index: 4580650 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4520. Min Act: -0.1700
Data Index: 1492974 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4520. Min Act: -0.1700
Data Index: 8581411 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4520. Min Act: -0.1700
Data Index: 6981814 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4208. Min Act: -0.1700
Data Index: 1630977 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4208. Min Act: -0.1700
Data Index: 2796848 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8895. Min Range: -6.8895
Max Act: 6.4208. Min Act: -0.1700
Data Index: 1246098 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19