Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1818. Min Range: -6.1818
Max Act: 6.1818. Min Act: -0.1700
Data Index: 3328605 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1818. Min Range: -6.1818
Max Act: 6.0881. Min Act: -0.1700
Data Index: 2120970 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.9631. Min Act: -0.1700
Data Index: 7949847 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2585591 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3713490 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.8693. Min Act: -0.1700
Data Index: 7299283 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.8068. Min Act: -0.1700
Data Index: 82069 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.8068. Min Act: -0.1700
Data Index: 44930 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.8068. Min Act: -0.1700
Data Index: 8355908 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7756. Min Act: -0.1700
Data Index: 718687 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7756. Min Act: -0.1700
Data Index: 47603 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5640996 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7756. Min Act: -0.1700
Data Index: 4258973 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7443. Min Act: -0.1700
Data Index: 5257487 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7131. Min Act: -0.1700
Data Index: 7010256 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7131. Min Act: -0.1700
Data Index: 8784524 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7131. Min Act: -0.1700
Data Index: 1843553 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3385374 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.6818. Min Act: -0.1700
Data Index: 3328628 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1818. Min Range: -6.1818
Max Act: 5.6818. Min Act: -0.1700
Data Index: 2572875 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19