Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1125. Min Range: -8.1125
Max Act: 8.1125. Min Act: -0.1700
Data Index: 2698830 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1125. Min Range: -8.1125
Max Act: 8.0500. Min Act: -0.1700
Data Index: 8079405 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.9562. Min Act: -0.1700
Data Index: 7470967 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.8937. Min Act: -0.1700
Data Index: 6901812 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.8625. Min Act: -0.1700
Data Index: 1588898 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.8625. Min Act: -0.1700
Data Index: 4266117 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.8625. Min Act: -0.1700
Data Index: 3883059 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.8312. Min Act: -0.1700
Data Index: 3143450 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.7062. Min Act: -0.1700
Data Index: 7431910 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.6750. Min Act: -0.1700
Data Index: 8335965 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.6750. Min Act: -0.1700
Data Index: 7857898 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.6750. Min Act: -0.1700
Data Index: 8268236 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5812. Min Act: -0.1700
Data Index: 3359648 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5812. Min Act: -0.1700
Data Index: 7632725 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5500. Min Act: -0.1700
Data Index: 7187015 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5500. Min Act: -0.1700
Data Index: 112002 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5500. Min Act: -0.1700
Data Index: 1409426 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5812. Min Act: -0.1700
Data Index: 3610791 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.5500. Min Act: -0.1700
Data Index: 5596852 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1125. Min Range: -8.1125
Max Act: 7.4875. Min Act: -0.1700
Data Index: 6042800 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19