Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4388086 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6666969 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5970. Min Act: -0.1700
Data Index: 2835364 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5658. Min Act: -0.1700
Data Index: 8280057 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5033. Min Act: -0.1700
Data Index: 1911461 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5033. Min Act: -0.1700
Data Index: 3695148 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5033. Min Act: -0.1700
Data Index: 3495340 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1442864 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.4720. Min Act: -0.1700
Data Index: 2890793 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.4720. Min Act: -0.1700
Data Index: 1749027 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.4720. Min Act: -0.1700
Data Index: 5397426 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3783. Min Act: -0.1700
Data Index: 3484079 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.4095. Min Act: -0.1700
Data Index: 6156927 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.4095. Min Act: -0.1700
Data Index: 761294 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3783. Min Act: -0.1700
Data Index: 8651091 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3783. Min Act: -0.1700
Data Index: 6390382 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3783. Min Act: -0.1700
Data Index: 7840398 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3470. Min Act: -0.1700
Data Index: 7655843 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3783. Min Act: -0.1700
Data Index: 7781437 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3655155 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19