Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.8793. Min Act: -0.1700
Data Index: 2963015 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.7855. Min Act: -0.1700
Data Index: 798429 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.7230. Min Act: -0.1700
Data Index: 1602320 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.6293. Min Act: -0.1700
Data Index: 6654666 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.5355. Min Act: -0.1700
Data Index: 6786549 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.5355. Min Act: -0.1700
Data Index: 6731181 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.5043. Min Act: -0.1700
Data Index: 3745133 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.5043. Min Act: -0.1700
Data Index: 5629041 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.4730. Min Act: -0.1700
Data Index: 1152800 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.4105. Min Act: -0.1700
Data Index: 1811796 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.4105. Min Act: -0.1700
Data Index: 3587991 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3793. Min Act: -0.1700
Data Index: 2829699 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.4105. Min Act: -0.1700
Data Index: 3587992 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3480. Min Act: -0.1700
Data Index: 6756161 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3168. Min Act: -0.1700
Data Index: 3745134 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3168. Min Act: -0.1700
Data Index: 4113049 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.2855. Min Act: -0.1700
Data Index: 2487774 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.2543. Min Act: -0.1700
Data Index: 6357666 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.3168. Min Act: -0.1700
Data Index: 6069457 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8793. Min Range: -7.8793
Max Act: 7.2855. Min Act: -0.1700
Data Index: 4690224 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19