Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5875. Min Range: -6.5875
Max Act: 6.5875. Min Act: -0.1700
Data Index: 6154678 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.9937. Min Act: -0.1700
Data Index: 3907533 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.9000. Min Act: -0.1700
Data Index: 8063673 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.9000. Min Act: -0.1700
Data Index: 7345929 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.9000. Min Act: -0.1700
Data Index: 1654063 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.8375. Min Act: -0.1700
Data Index: 338458 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7750. Min Act: -0.1700
Data Index: 7996971 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7437. Min Act: -0.1700
Data Index: 8049853 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7750. Min Act: -0.1700
Data Index: 4519569 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7437. Min Act: -0.1700
Data Index: 1689768 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7125. Min Act: -0.1700
Data Index: 7482379 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.7125. Min Act: -0.1700
Data Index: 3985476 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 8762589 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 158523 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 2551335 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 1746483 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 4125262 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 5302532 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.6187. Min Act: -0.1700
Data Index: 3712286 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5875. Min Range: -6.5875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 3111004 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19