Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4376. Min Range: -6.4376
Max Act: 6.4376. Min Act: -0.1700
Data Index: 733525 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4376. Min Range: -6.4376
Max Act: 6.3751. Min Act: -0.1700
Data Index: 4106743 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4376. Min Range: -6.4376
Max Act: 6.2813. Min Act: -0.1700
Data Index: 4106741 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4376. Min Range: -6.4376
Max Act: 6.2813. Min Act: -0.1700
Data Index: 8566506 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4376. Min Range: -6.4376
Max Act: 6.1251. Min Act: -0.1700
Data Index: 4415084 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.9688. Min Act: -0.1700
Data Index: 4734511 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.9063. Min Act: -0.1700
Data Index: 4560541 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.9063. Min Act: -0.1700
Data Index: 2289327 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.8751. Min Act: -0.1700
Data Index: 3149113 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.8751. Min Act: -0.1700
Data Index: 1988714 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.8438. Min Act: -0.1700
Data Index: 7482163 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.8126. Min Act: -0.1700
Data Index: 8014921 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7813. Min Act: -0.1700
Data Index: 1626566 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7501. Min Act: -0.1700
Data Index: 8515911 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7501. Min Act: -0.1700
Data Index: 351061 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7188. Min Act: -0.1700
Data Index: 40182 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7188. Min Act: -0.1700
Data Index: 3799156 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7188. Min Act: -0.1700
Data Index: 5065899 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7188. Min Act: -0.1700
Data Index: 2674015 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4376. Min Range: -6.4376
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1394403 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19