Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.3687. Min Act: -0.1700
Data Index: 6885707 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.3375. Min Act: -0.1700
Data Index: 5724985 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.2750. Min Act: -0.1700
Data Index: 6084299 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.1812. Min Act: -0.1700
Data Index: 4139668 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.1187. Min Act: -0.1700
Data Index: 153479 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.1500. Min Act: -0.1700
Data Index: 2438295 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.1500. Min Act: -0.1700
Data Index: 3972350 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.1187. Min Act: -0.1700
Data Index: 8486285 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.0562. Min Act: -0.1700
Data Index: 59183 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.0250. Min Act: -0.1700
Data Index: 7655474 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3687. Min Range: -7.3687
Max Act: 7.0250. Min Act: -0.1700
Data Index: 2161101 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9937. Min Act: -0.1700
Data Index: 3482197 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9937. Min Act: -0.1700
Data Index: 7898856 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9937. Min Act: -0.1700
Data Index: 5918044 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9937. Min Act: -0.1700
Data Index: 5163574 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9937. Min Act: -0.1700
Data Index: 4499083 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9625. Min Act: -0.1700
Data Index: 1248714 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9625. Min Act: -0.1700
Data Index: 3900231 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9000. Min Act: -0.1700
Data Index: 4258867 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3687. Min Range: -7.3687
Max Act: 6.9312. Min Act: -0.1700
Data Index: 4339829 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19