Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.4057. Min Act: -0.1700
Data Index: 8724404 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.3744. Min Act: -0.1700
Data Index: 5028400 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.3587. Min Act: -0.1700
Data Index: 841228 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2488. Min Act: -0.1700
Data Index: 4039094 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2331. Min Act: -0.1700
Data Index: 4118347 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2488. Min Act: -0.1700
Data Index: 2140 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2174. Min Act: -0.1700
Data Index: 2084698 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2016. Min Act: -0.1700
Data Index: 6930179 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.2016. Min Act: -0.1700
Data Index: 2544904 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1859. Min Act: -0.1700
Data Index: 3268638 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1702. Min Act: -0.1700
Data Index: 4529512 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1702. Min Act: -0.1700
Data Index: 830428 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1544. Min Act: -0.1700
Data Index: 131248 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1387. Min Act: -0.1700
Data Index: 3469625 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1387. Min Act: -0.1700
Data Index: 8197780 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1387. Min Act: -0.1700
Data Index: 1521930 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1229. Min Act: -0.1700
Data Index: 4144927 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1229. Min Act: -0.1700
Data Index: 4472918 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1072. Min Act: -0.1700
Data Index: 4351218 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4057. Min Range: -3.4057
Max Act: 3.1229. Min Act: -0.1700
Data Index: 2065100 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19