Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1517 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4995. Min Range: -9.4995
Max Act: 9.4995. Min Act: -0.1700
Data Index: 2555532 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4995. Min Range: -9.4995
Max Act: 9.4995. Min Act: -0.1700
Data Index: 351982 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4995. Min Range: -9.4995
Max Act: 9.4995. Min Act: -0.1700
Data Index: 8016893 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4995. Min Range: -9.4995
Max Act: 9.1870. Min Act: -0.1700
Data Index: 6743453 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4995. Min Range: -9.4995
Max Act: 9.1245. Min Act: -0.1700
Data Index: 7514731 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8745. Min Act: -0.1700
Data Index: 4494021 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8745. Min Act: -0.1700
Data Index: 7421441 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8745. Min Act: -0.1700
Data Index: 163455 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8120. Min Act: -0.1700
Data Index: 7392247 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8120. Min Act: -0.1700
Data Index: 4699970 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.8120. Min Act: -0.1700
Data Index: 6689687 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.7495. Min Act: -0.1700
Data Index: 7850204 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.7495. Min Act: -0.1700
Data Index: 3005882 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.6870. Min Act: -0.1700
Data Index: 3627938 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.6870. Min Act: -0.1700
Data Index: 1079214 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.6245. Min Act: -0.1700
Data Index: 2178318 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.4995. Min Act: -0.1700
Data Index: 3852499 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.4995. Min Act: -0.1700
Data Index: 6895175 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.4995. Min Act: -0.1700
Data Index: 3065351 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4995. Min Range: -9.4995
Max Act: 8.4995. Min Act: -0.1700
Data Index: 3431372 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19