Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1913 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.6955. Min Act: -0.1700
Data Index: 4500454 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.4142. Min Act: -0.1700
Data Index: 1225886 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.4142. Min Act: -0.1700
Data Index: 7272544 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4357974 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4115491 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2892. Min Act: -0.1700
Data Index: 2527209 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2267. Min Act: -0.1700
Data Index: 2927609 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2580. Min Act: -0.1700
Data Index: 1931982 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.2267. Min Act: -0.1700
Data Index: 8559498 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1955. Min Act: -0.1700
Data Index: 1492594 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1642. Min Act: -0.1700
Data Index: 7485530 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1955. Min Act: -0.1700
Data Index: 7643043 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1017. Min Act: -0.1700
Data Index: 3839066 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1642. Min Act: -0.1700
Data Index: 1785442 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1880064 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.1330. Min Act: -0.1700
Data Index: 2305887 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.0705. Min Act: -0.1700
Data Index: 1195828 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.0392. Min Act: -0.1700
Data Index: 446415 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.0705. Min Act: -0.1700
Data Index: 4323583 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6955. Min Range: -5.6955
Max Act: 5.0705. Min Act: -0.1700
Data Index: 6991735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19