Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3250. Min Range: -8.3250
Max Act: 8.3250. Min Act: -0.1700
Data Index: 4158595 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3250. Min Range: -8.3250
Max Act: 8.1688. Min Act: -0.1700
Data Index: 5582794 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3250. Min Range: -8.3250
Max Act: 8.1063. Min Act: -0.1700
Data Index: 3165896 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3250. Min Range: -8.3250
Max Act: 8.0750. Min Act: -0.1700
Data Index: 4718953 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3250. Min Range: -8.3250
Max Act: 8.0125. Min Act: -0.1700
Data Index: 2254357 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.9500. Min Act: -0.1700
Data Index: 4158611 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.8875. Min Act: -0.1700
Data Index: 8315787 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.8250. Min Act: -0.1700
Data Index: 5269515 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.7000. Min Act: -0.1700
Data Index: 2825709 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.7313. Min Act: -0.1700
Data Index: 1848782 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.7000. Min Act: -0.1700
Data Index: 2111513 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.7000. Min Act: -0.1700
Data Index: 4456930 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.7000. Min Act: -0.1700
Data Index: 4204139 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.6688. Min Act: -0.1700
Data Index: 719624 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.6375. Min Act: -0.1700
Data Index: 2158830 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.6375. Min Act: -0.1700
Data Index: 5155265 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.6063. Min Act: -0.1700
Data Index: 4518475 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.5438. Min Act: -0.1700
Data Index: 1988847 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.5438. Min Act: -0.1700
Data Index: 4573480 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3250. Min Range: -8.3250
Max Act: 7.5438. Min Act: -0.1700
Data Index: 245959 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19