Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5430. Min Range: -6.5430
Max Act: 6.5430. Min Act: -0.1700
Data Index: 1341371 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5430. Min Range: -6.5430
Max Act: 6.0742. Min Act: -0.1700
Data Index: 3335989 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.8867. Min Act: -0.1700
Data Index: 2639272 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.8867. Min Act: -0.1700
Data Index: 149977 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.8555. Min Act: -0.1700
Data Index: 7134793 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.8555. Min Act: -0.1700
Data Index: 5096548 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.8242. Min Act: -0.1700
Data Index: 720773 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.6680. Min Act: -0.1700
Data Index: 5830775 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.6367. Min Act: -0.1700
Data Index: 4309272 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.6367. Min Act: -0.1700
Data Index: 5618220 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.6055. Min Act: -0.1700
Data Index: 3010491 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5742. Min Act: -0.1700
Data Index: 1492687 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5742. Min Act: -0.1700
Data Index: 8482894 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5742. Min Act: -0.1700
Data Index: 4795700 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6621731 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6300736 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5117. Min Act: -0.1700
Data Index: 852143 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.4805. Min Act: -0.1700
Data Index: 3407390 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.5117. Min Act: -0.1700
Data Index: 3505082 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5430. Min Range: -6.5430
Max Act: 5.4805. Min Act: -0.1700
Data Index: 500908 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19