Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.8164. Min Act: -0.1700
Data Index: 6683303 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.5039. Min Act: -0.1700
Data Index: 7511469 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.2539. Min Act: -0.1700
Data Index: 6493171 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.1914. Min Act: -0.1700
Data Index: 1650713 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.0664. Min Act: -0.1700
Data Index: 7868779 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.0664. Min Act: -0.1700
Data Index: 3957163 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.0664. Min Act: -0.1700
Data Index: 1990741 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.0664. Min Act: -0.1700
Data Index: 370805 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8164. Min Range: -8.8164
Max Act: 8.0039. Min Act: -0.1700
Data Index: 84546 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9727. Min Act: -0.1700
Data Index: 7640540 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9727. Min Act: -0.1700
Data Index: 1606184 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9727. Min Act: -0.1700
Data Index: 5520248 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9414. Min Act: -0.1700
Data Index: 1915098 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9102. Min Act: -0.1700
Data Index: 5867369 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9102. Min Act: -0.1700
Data Index: 5494239 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9102. Min Act: -0.1700
Data Index: 127841 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.9102. Min Act: -0.1700
Data Index: 4218913 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.8164. Min Act: -0.1700
Data Index: 1585774 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.8164. Min Act: -0.1700
Data Index: 1843989 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8164. Min Range: -8.8164
Max Act: 7.7539. Min Act: -0.1700
Data Index: 343597 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19