Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5721 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.4014. Min Act: -0.1700
Data Index: 210999 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.3389. Min Act: -0.1700
Data Index: 2217564 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.2764. Min Act: -0.1700
Data Index: 2917941 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.2139. Min Act: -0.1700
Data Index: 1622648 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.1514. Min Act: -0.1700
Data Index: 6525356 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.1514. Min Act: -0.1700
Data Index: 8348965 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0889. Min Act: -0.1700
Data Index: 2365386 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0889. Min Act: -0.1700
Data Index: 4230837 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0889. Min Act: -0.1700
Data Index: 4592085 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0264. Min Act: -0.1700
Data Index: 2212991 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0264. Min Act: -0.1700
Data Index: 5705445 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0264. Min Act: -0.1700
Data Index: 5266701 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0264. Min Act: -0.1700
Data Index: 3958472 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 5137557 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4014. Min Range: -8.4014
Max Act: 8.0264. Min Act: -0.1700
Data Index: 593796 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 907493 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 3178193 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 1627127 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 2349780 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4014. Min Range: -8.4014
Max Act: 7.9639. Min Act: -0.1700
Data Index: 8028732 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19