Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2814. Min Act: -0.1700
Data Index: 1258272 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2814. Min Act: -0.1700
Data Index: 527991 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2501. Min Act: -0.1700
Data Index: 3025748 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2189. Min Act: -0.1700
Data Index: 6000243 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1876. Min Act: -0.1700
Data Index: 1678899 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2189. Min Act: -0.1700
Data Index: 7045000 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.2189. Min Act: -0.1700
Data Index: 3879698 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1876. Min Act: -0.1700
Data Index: 3395987 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1876. Min Act: -0.1700
Data Index: 4384352 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1563. Min Act: -0.1700
Data Index: 7233501 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1563. Min Act: -0.1700
Data Index: 2512609 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1563. Min Act: -0.1700
Data Index: 7250249 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1251. Min Act: -0.1700
Data Index: 6241811 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.1251. Min Act: -0.1700
Data Index: 6327046 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0938. Min Act: -0.1700
Data Index: 5093263 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0938. Min Act: -0.1700
Data Index: 2400371 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0938. Min Act: -0.1700
Data Index: 313419 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0938. Min Act: -0.1700
Data Index: 1890698 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0938. Min Act: -0.1700
Data Index: 5155304 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2814. Min Range: -4.2814
Max Act: 4.0626. Min Act: -0.1700
Data Index: 613807 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19