Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1634. Min Range: -6.1634
Max Act: 6.1634. Min Act: -0.1700
Data Index: 2739647 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.8509. Min Act: -0.1700
Data Index: 8441871 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7892071 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7429379 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7884. Min Act: -0.1700
Data Index: 5115201 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7884. Min Act: -0.1700
Data Index: 3539256 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7572. Min Act: -0.1700
Data Index: 2879530 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7884. Min Act: -0.1700
Data Index: 4598729 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7572. Min Act: -0.1700
Data Index: 5366308 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7259. Min Act: -0.1700
Data Index: 7111715 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2393733 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6947. Min Act: -0.1700
Data Index: 7551442 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7259. Min Act: -0.1700
Data Index: 1434169 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.7259. Min Act: -0.1700
Data Index: 6587150 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6947. Min Act: -0.1700
Data Index: 6838004 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6634. Min Act: -0.1700
Data Index: 6578322 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6947. Min Act: -0.1700
Data Index: 7317328 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6947. Min Act: -0.1700
Data Index: 679606 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6322. Min Act: -0.1700
Data Index: 991001 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1634. Min Range: -6.1634
Max Act: 5.6634. Min Act: -0.1700
Data Index: 4700636 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19