Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5620 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4626. Min Range: -5.4626
Max Act: 5.4626. Min Act: -0.1700
Data Index: 4052954 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4626. Min Range: -5.4626
Max Act: 5.1501. Min Act: -0.1700
Data Index: 8057631 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4626. Min Range: -5.4626
Max Act: 5.0876. Min Act: -0.1700
Data Index: 6251865 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4626. Min Range: -5.4626
Max Act: 5.0251. Min Act: -0.1700
Data Index: 5675438 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.9938. Min Act: -0.1700
Data Index: 1905751 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.9938. Min Act: -0.1700
Data Index: 2404422 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.8688. Min Act: -0.1700
Data Index: 3197074 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4661579 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.8376. Min Act: -0.1700
Data Index: 4785279 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1050316 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.7751. Min Act: -0.1700
Data Index: 8107883 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4835517 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.7126. Min Act: -0.1700
Data Index: 1633714 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.7126. Min Act: -0.1700
Data Index: 6664568 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 4867364 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.7126. Min Act: -0.1700
Data Index: 6261202 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 5479882 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.6501. Min Act: -0.1700
Data Index: 754693 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 3028636 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4626. Min Range: -5.4626
Max Act: 4.6501. Min Act: -0.1700
Data Index: 743939 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19