Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.9250. Min Act: -0.1700
Data Index: 349313 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.8000. Min Act: -0.1700
Data Index: 7769872 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.7063. Min Act: -0.1700
Data Index: 3664530 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2040221 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6438. Min Act: -0.1700
Data Index: 1370790 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6438. Min Act: -0.1700
Data Index: 3511936 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 4296579 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 4579265 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 616849 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5813. Min Act: -0.1700
Data Index: 6000556 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5500. Min Act: -0.1700
Data Index: 4763165 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5500. Min Act: -0.1700
Data Index: 7150838 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5500. Min Act: -0.1700
Data Index: 5989782 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 4364541 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 2493630 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.4875. Min Act: -0.1700
Data Index: 6141745 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 7752437 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.4875. Min Act: -0.1700
Data Index: 1679995 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 1244565 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9250. Min Range: -5.9250
Max Act: 5.4875. Min Act: -0.1700
Data Index: 5653957 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19