Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.8883. Min Act: -0.1700
Data Index: 7956116 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.8258. Min Act: -0.1700
Data Index: 5867116 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.8258. Min Act: -0.1700
Data Index: 772501 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.8258. Min Act: -0.1700
Data Index: 5138169 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.7008. Min Act: -0.1700
Data Index: 1912647 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.6383. Min Act: -0.1700
Data Index: 8714704 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.6383. Min Act: -0.1700
Data Index: 1662802 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.6383. Min Act: -0.1700
Data Index: 8162277 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.5133. Min Act: -0.1700
Data Index: 2767985 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.5133. Min Act: -0.1700
Data Index: 6274930 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.5758. Min Act: -0.1700
Data Index: 2549906 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.5133. Min Act: -0.1700
Data Index: 7813608 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.4820. Min Act: -0.1700
Data Index: 8095998 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.4195. Min Act: -0.1700
Data Index: 3977095 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.4195. Min Act: -0.1700
Data Index: 3580304 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.3883. Min Act: -0.1700
Data Index: 5480157 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.3883. Min Act: -0.1700
Data Index: 2769695 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.3258. Min Act: -0.1700
Data Index: 3877102 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.3570. Min Act: -0.1700
Data Index: 1500100 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8883. Min Range: -7.8883
Max Act: 7.3570. Min Act: -0.1700
Data Index: 2248845 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19