Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0156. Min Range: -10.0156
Max Act: 10.0156. Min Act: -0.1700
Data Index: 3932565 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.6406. Min Act: -0.1700
Data Index: 304955 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.6406. Min Act: -0.1700
Data Index: 785899 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.5781. Min Act: -0.1700
Data Index: 7589860 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.5156. Min Act: -0.1700
Data Index: 2621678 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 4413801 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 3369731 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 3108483 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 3371313 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 2582528 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 7775914 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3906. Min Act: -0.1700
Data Index: 1479633 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.4531. Min Act: -0.1700
Data Index: 8699803 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3906. Min Act: -0.1700
Data Index: 6254221 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3906. Min Act: -0.1700
Data Index: 8381533 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3906. Min Act: -0.1700
Data Index: 565466 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3906. Min Act: -0.1700
Data Index: 7665968 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3281. Min Act: -0.1700
Data Index: 6990244 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3281. Min Act: -0.1700
Data Index: 5391238 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0156. Min Range: -10.0156
Max Act: 9.3281. Min Act: -0.1700
Data Index: 1939330 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19