Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.5942. Min Act: -0.1700
Data Index: 1660039 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.2817. Min Act: -0.1700
Data Index: 66789 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.3129. Min Act: -0.1700
Data Index: 7470611 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.2504. Min Act: -0.1700
Data Index: 2890477 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.1567. Min Act: -0.1700
Data Index: 1758941 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0942. Min Act: -0.1700
Data Index: 1517714 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0942. Min Act: -0.1700
Data Index: 4220536 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.1254. Min Act: -0.1700
Data Index: 3010398 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0942. Min Act: -0.1700
Data Index: 8468447 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0942. Min Act: -0.1700
Data Index: 8018438 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0629. Min Act: -0.1700
Data Index: 2631073 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0629. Min Act: -0.1700
Data Index: 8286746 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0629. Min Act: -0.1700
Data Index: 5994530 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0317. Min Act: -0.1700
Data Index: 8723624 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0317. Min Act: -0.1700
Data Index: 2769109 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0317. Min Act: -0.1700
Data Index: 860458 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0004. Min Act: -0.1700
Data Index: 4549372 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5942. Min Range: -7.5942
Max Act: 7.0004. Min Act: -0.1700
Data Index: 4934301 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5942. Min Range: -7.5942
Max Act: 6.9692. Min Act: -0.1700
Data Index: 1418076 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5942. Min Range: -7.5942
Max Act: 6.9379. Min Act: -0.1700
Data Index: 5790077 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19