Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1393 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2491. Min Range: -6.2491
Max Act: 6.2491. Min Act: -0.1700
Data Index: 845904 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2491. Min Range: -6.2491
Max Act: 6.0616. Min Act: -0.1700
Data Index: 6629361 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.9991. Min Act: -0.1700
Data Index: 6355202 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.9679. Min Act: -0.1700
Data Index: 3778868 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.8741. Min Act: -0.1700
Data Index: 1281800 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.8116. Min Act: -0.1700
Data Index: 8259808 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 6323230 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.8116. Min Act: -0.1700
Data Index: 3778867 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4570732 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.8429. Min Act: -0.1700
Data Index: 6354093 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 8170181 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 6547199 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5173081 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 8308995 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 5857338 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 1175360 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 5246757 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7207043 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7804. Min Act: -0.1700
Data Index: 73427 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2491. Min Range: -6.2491
Max Act: 5.7491. Min Act: -0.1700
Data Index: 3138427 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19