Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2129. Min Range: -9.2129
Max Act: 9.2129. Min Act: -0.1700
Data Index: 1187029 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2129. Min Range: -9.2129
Max Act: 9.0879. Min Act: -0.1700
Data Index: 3534127 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.6504. Min Act: -0.1700
Data Index: 636213 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.5879. Min Act: -0.1700
Data Index: 6774742 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.5254. Min Act: -0.1700
Data Index: 8612822 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.4629. Min Act: -0.1700
Data Index: 7181764 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.3379. Min Act: -0.1700
Data Index: 3356091 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.3379. Min Act: -0.1700
Data Index: 4206724 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.2754. Min Act: -0.1700
Data Index: 4713405 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.2754. Min Act: -0.1700
Data Index: 300446 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.1504. Min Act: -0.1700
Data Index: 795707 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.1504. Min Act: -0.1700
Data Index: 992135 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.2129. Min Act: -0.1700
Data Index: 7127962 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.0879. Min Act: -0.1700
Data Index: 8612257 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.0254. Min Act: -0.1700
Data Index: 5464636 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.0879. Min Act: -0.1700
Data Index: 1550494 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.0879. Min Act: -0.1700
Data Index: 5800332 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2129. Min Range: -9.2129
Max Act: 8.0254. Min Act: -0.1700
Data Index: 166537 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2129. Min Range: -9.2129
Max Act: 7.9629. Min Act: -0.1700
Data Index: 2933838 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2129. Min Range: -9.2129
Max Act: 7.9004. Min Act: -0.1700
Data Index: 3011087 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19