Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.7047. Min Act: -0.1700
Data Index: 6557934 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.3609. Min Act: -0.1700
Data Index: 5514610 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.3296. Min Act: -0.1700
Data Index: 4262616 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.2359. Min Act: -0.1700
Data Index: 5474642 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1734. Min Act: -0.1700
Data Index: 8374080 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1734. Min Act: -0.1700
Data Index: 8560402 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1421. Min Act: -0.1700
Data Index: 6197287 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1109. Min Act: -0.1700
Data Index: 3198601 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1109. Min Act: -0.1700
Data Index: 515626 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0796. Min Act: -0.1700
Data Index: 8412306 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.1109. Min Act: -0.1700
Data Index: 6511967 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0171. Min Act: -0.1700
Data Index: 2030400 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 7801895 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 7884413 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 4698684 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 423762 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 5229127 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0483. Min Act: -0.1700
Data Index: 1777359 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0171. Min Act: -0.1700
Data Index: 5698642 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7047. Min Range: -4.7047
Max Act: 4.0171. Min Act: -0.1700
Data Index: 3789650 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19