Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1895. Min Range: -11.1895
Max Act: 11.1895. Min Act: -0.1700
Data Index: 3060642 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1895. Min Range: -11.1895
Max Act: 11.1270. Min Act: -0.1700
Data Index: 6801418 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1895. Min Range: -11.1895
Max Act: 11.1270. Min Act: -0.1700
Data Index: 3431228 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1895. Min Range: -11.1895
Max Act: 11.0645. Min Act: -0.1700
Data Index: 3249480 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.9395. Min Act: -0.1700
Data Index: 1595634 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.9395. Min Act: -0.1700
Data Index: 3871336 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.7520. Min Act: -0.1700
Data Index: 8613168 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.6895. Min Act: -0.1700
Data Index: 391791 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.6270. Min Act: -0.1700
Data Index: 6323569 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.5645. Min Act: -0.1700
Data Index: 2944640 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.5645. Min Act: -0.1700
Data Index: 3249495 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.6270. Min Act: -0.1699
Data Index: 7794307 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.5645. Min Act: -0.1700
Data Index: 6727398 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.5020. Min Act: -0.1700
Data Index: 6132990 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.5020. Min Act: -0.1700
Data Index: 4703912 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.4395. Min Act: -0.1700
Data Index: 6801417 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.4395. Min Act: -0.1700
Data Index: 6439155 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.3770. Min Act: -0.1700
Data Index: 5937380 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.3145. Min Act: -0.1700
Data Index: 8702390 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1895. Min Range: -11.1895
Max Act: 10.3770. Min Act: -0.1700
Data Index: 6084236 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19