Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.2144. Min Act: -0.1700
Data Index: 129974 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1832. Min Act: -0.1700
Data Index: 5010560 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1519. Min Act: -0.1700
Data Index: 3253911 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1519. Min Act: -0.1700
Data Index: 3607903 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1519. Min Act: -0.1700
Data Index: 1979627 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1207. Min Act: -0.1700
Data Index: 1908700 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.1207. Min Act: -0.1700
Data Index: 5010567 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.0894. Min Act: -0.1700
Data Index: 7621842 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.0269. Min Act: -0.1700
Data Index: 1730506 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2144. Min Range: -6.2144
Max Act: 6.0269. Min Act: -0.1700
Data Index: 1469837 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9644. Min Act: -0.1700
Data Index: 5755883 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9957. Min Act: -0.1700
Data Index: 8803531 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9957. Min Act: -0.1700
Data Index: 5755884 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9957. Min Act: -0.1700
Data Index: 5095442 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9957. Min Act: -0.1700
Data Index: 5430005 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9332. Min Act: -0.1700
Data Index: 1469836 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9644. Min Act: -0.1700
Data Index: 6633684 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5993148 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9019. Min Act: -0.1700
Data Index: 4961155 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2144. Min Range: -6.2144
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7730671 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19