Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.3094. Min Act: -0.1700
Data Index: 8527523 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.2469. Min Act: -0.1700
Data Index: 8092289 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.2469. Min Act: -0.1700
Data Index: 1081933 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.3094. Min Act: -0.1700
Data Index: 4515999 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.2469. Min Act: -0.1700
Data Index: 1132662 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.1844. Min Act: -0.1700
Data Index: 7224863 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.1219. Min Act: -0.1700
Data Index: 3748218 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.1219. Min Act: -0.1700
Data Index: 4202237 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3094. Min Range: -9.3094
Max Act: 9.0594. Min Act: -0.1700
Data Index: 6552792 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.9969. Min Act: -0.1700
Data Index: 1016417 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.9969. Min Act: -0.1700
Data Index: 3674966 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8719. Min Act: -0.1700
Data Index: 5165299 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8719. Min Act: -0.1700
Data Index: 1263021 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8719. Min Act: -0.1700
Data Index: 15070 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8719. Min Act: -0.1700
Data Index: 4733294 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8719. Min Act: -0.1700
Data Index: 8396820 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8094. Min Act: -0.1700
Data Index: 3190329 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8094. Min Act: -0.1700
Data Index: 1676908 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8094. Min Act: -0.1700
Data Index: 6152970 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3094. Min Range: -9.3094
Max Act: 8.8094. Min Act: -0.1700
Data Index: 2099346 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19