Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.6087. Min Act: -0.1700
Data Index: 7055704 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.5774. Min Act: -0.1700
Data Index: 5414756 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.3587. Min Act: -0.1700
Data Index: 236190 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.3274. Min Act: -0.1700
Data Index: 6918180 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.3274. Min Act: -0.1700
Data Index: 7437972 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.2024. Min Act: -0.1700
Data Index: 8293937 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.2337. Min Act: -0.1700
Data Index: 7809481 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.2337. Min Act: -0.1700
Data Index: 1886715 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1712. Min Act: -0.1700
Data Index: 6857093 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1399. Min Act: -0.1700
Data Index: 7409725 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1712. Min Act: -0.1700
Data Index: 6426523 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1399. Min Act: -0.1700
Data Index: 2602054 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1087. Min Act: -0.1700
Data Index: 4302124 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1087. Min Act: -0.1700
Data Index: 6340152 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1087. Min Act: -0.1700
Data Index: 4003959 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.0774. Min Act: -0.1700
Data Index: 1239666 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.1087. Min Act: -0.1700
Data Index: 6751041 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.0774. Min Act: -0.1700
Data Index: 5181139 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.0462. Min Act: -0.1700
Data Index: 6576367 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6087. Min Range: -6.6087
Max Act: 6.0462. Min Act: -0.1700
Data Index: 3583131 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19