Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1890 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.9122. Min Act: -0.1700
Data Index: 1498088 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.9122. Min Act: -0.1700
Data Index: 7435438 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8809. Min Act: -0.1700
Data Index: 1622904 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8809. Min Act: -0.1700
Data Index: 8467194 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8497. Min Act: -0.1700
Data Index: 6781855 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8497. Min Act: -0.1700
Data Index: 7096173 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8497. Min Act: -0.1700
Data Index: 2551176 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8497. Min Act: -0.1700
Data Index: 4106605 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8184. Min Act: -0.1700
Data Index: 1953164 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7872. Min Act: -0.1700
Data Index: 116971 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8184. Min Act: -0.1700
Data Index: 5937842 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 5837239 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7872. Min Act: -0.1700
Data Index: 1357514 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 2113 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 8211908 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 1659250 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 8500948 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7559. Min Act: -0.1700
Data Index: 7454803 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.6934. Min Act: -0.1700
Data Index: 5231278 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7247. Min Act: -0.1700
Data Index: 6537210 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19